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. 105
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions within sentences

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

    Text preceding semicolons

    np_acts-logits-general · gemini-2.0-flash

    ; and

    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
    .
    -0.69
     or
    -0.57
     and
    -0.56
    ,
    -0.53
    or
    -0.50
    V
    -0.48
    Я
    -0.47
    e
    -0.47
     
    -0.46
    U
    -0.46
    POSITIVE LOGITS
    DockStyle
    0.95
     وتسجيلات
    0.92
    rungsseite
    0.90
     Référence
    0.90
     otomatig
    0.88
     ModelExpression
    0.88
    RTLD
    0.87
    SourceChecksum
    0.86
    Hochspringen
    0.84
     Nark
    0.83
    Activations Density 0.173%

    No Known Activations