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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 122903
    Prev
    Next
    INDEX
    Explanations

    occurrences of pixel measurements in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    tvguidetime
    -0.60
    providedIn
    -0.58
    \{\\
    -0.54
    setof
    -0.53
    脚注の使い方
    -0.53
    setDo
    -0.52
    存于互联网档案馆
    -0.50
    withIdentifier
    -0.50
    subpackage
    -0.50
    WebServlet
    -0.50
    POSITIVE LOGITS
    px
    1.17
     px
    1.08
    Px
    1.04
     PX
    1.02
    PX
    0.98
     Px
    0.93
    Pixels
    0.73
     Pixels
    0.70
    Pixel
    0.67
     Pixel
    0.65
    Activations Density 0.003%

    No Known Activations