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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 18-GEMMASCOPE-RES-16K
    6. 8649
    Prev
    Next
    INDEX
    Explanations

    punctuations and their associated contexts in the text

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

    Punctuation followed by capitalized words

    np_acts-logits-general · gemini-2.0-flash

    voiced, lecture, click, return

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     the
    -0.63
     that
    -0.49
     worker
    -0.46
    active
    -0.45
     player
    -0.44
    digo
    -0.43
     active
    -0.43
     some
    -0.41
     too
    -0.41
     a
    -0.41
    POSITIVE LOGITS
    ">//
    0.88
    !*\
    0.84
     oprot
    0.82
    帖最后由
    0.79
    #
    0.79
     autorytatywna
    0.78
    #+#
    0.78
    }`).
    0.75
     surla
    0.74
    EndGlobalSection
    0.74
    Activations Density 0.381%

    No Known Activations