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. 16-GEMMASCOPE-RES-16K
    6. 9027
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to effectiveness and change

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

    Following certain words, like nouns or adjectives

    np_acts-logits-general · gemini-2.0-flash

    historical precedent and differences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    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
    -0.54
    UnknownFields
    -0.53
    reactstrap
    -0.52
     zove
    -0.48
    KURZBESCHREIBUNG
    -0.47
     ((*
    -0.47
    medriver
    -0.45
     (*
    -0.44
    نسية
    -0.44
    ?".
    -0.43
    POSITIVE LOGITS
    Elsewhere
    0.72
    queryInterface
    0.69
     resourceCulture
    0.67
    HasAnnotation
    0.66
     Elsewhere
    0.64
    BeginContext
    0.64
     also
    0.63
    UnsafeEnabled
    0.62
    exitRule
    0.60
     también
    0.59
    Activations Density 0.441%

    No Known Activations