Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 7367
    Prev
    Next
    INDEX
    Explanations

    references to self-reflection and self-assessment in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    hyphenated compounds prefixed with “self-,” strongly activating on the hyphen and the ensuing term.

    oai_token-act-pair · gpt-5Triggered by @timna

    self

    np_max-act-logits · deepseek-r1Triggered by @arielgoldsteinlab

    The token "self" used as a prefix forming compound nouns related to autonomous actions or states (e.g., monitoring, assessment, regulation).

    eleuther_acts_top20 · deepseek-r1Triggered by @arielgoldsteinlab

    self

    np_max-act · gpt-5Triggered by @arielgoldsteinlab

    self

    np_max-act-logits · gpt-5Triggered by @arielgoldsteinlab

    hyphenated compound words starting with "self-".

    oai_token-act-pair · deepseek-r1Triggered by @arielgoldsteinlab
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -1.21
     snippetHide
    -1.02
    DockStyle
    -0.92
    ✨:
    -0.89
     дописавши
    -0.89
     utafitiHapana
    -0.83
    richTextPanel
    -0.81
    AnchorStyles
    -0.81
    StreetMap
    -0.80
     typelib
    -0.80
    POSITIVE LOGITS
     SELF
    1.54
     Self
    1.46
     self
    1.45
    SELF
    1.39
    Self
    1.36
    self
    1.27
     selves
    0.99
    ELF
    0.90
    elf
    0.90
    selves
    0.82
    Activations Density 0.066%

    No Known Activations