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. 84475
    Prev
    Next
    INDEX
    Explanations

    HTML link tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    endphp
    -0.80
    InSection
    -0.77
    omock
    -0.76
     snippetHide
    -0.76
     يتيمه
    -0.75
     doInBackground
    -0.75
     виправивши
    -0.74
    BufferException
    -0.73
    NameInMap
    -0.73
    extAlignment
    -0.72
    POSITIVE LOGITS
    stylesheet
    0.65
    link
    0.56
    import
    0.47
     link
    0.47
    include
    0.40
     inalámbrica
    0.38
     enlace
    0.37
    Link
    0.35
     scaricare
    0.34
    enlace
    0.33
    Activations Density 0.001%

    No Known Activations