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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 29291
    Prev
    Next
    INDEX
    Explanations

    the presence and repetition of the word "dash" and its variations in different contexts

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

    dash followed by specific nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    multirow
    -0.46
    RTLD
    -0.45
    viewType
    -0.45
     Lawler
    -0.43
    WEBPACK
    -0.41
     PVP
    -0.41
    <tr>
    -0.41
    OGND
    -0.41
    yyj
    -0.41
     ویکی‌پدی
    -0.40
    POSITIVE LOGITS
     Dash
    1.24
    Dash
    1.16
    dash
    1.11
     dash
    1.09
     DASH
    1.09
    DASH
    1.00
     Dashboard
    0.85
     dashboards
    0.85
     dashes
    0.84
     dashing
    0.82
    Activations Density 0.004%

    No Known Activations