Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12813
    Prev
    Next
    INDEX
    Explanations

    specific terms related to scientific data and research methodologies

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    GeoNames
    -0.52
    InjectAttribute
    -0.48
    Personendaten
    -0.47
    帖最后由
    -0.46
    IntoConstraints
    -0.44
     ComVisible
    -0.42
    
    -0.42
     AssemblyCulture
    -0.40
    WebServlet
    -0.39
     colspan
    -0.39
    POSITIVE LOGITS
    fører
    0.53
    ávajú
    0.50
     ribuan
    0.49
     lisäksi
    0.47
     congrès
    0.46
     whoſe
    0.46
     Deum
    0.46
    alakip
    0.45
     waaronder
    0.44
     sveta
    0.44
    Activations Density 0.737%

    No Known Activations