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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 21780
    Prev
    Next
    INDEX
    Explanations

    descriptions of surfaces characterized by their roughness or texture

    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
    DotNetBar
    -0.50
    enumii
    -0.47
    Minn
    -0.45
     optar
    -0.44
    ylase
    -0.44
     سكانية
    -0.44
    getItemId
    -0.43
    ؜
    -0.43
     cytok
    -0.43
    iibo
    -0.43
    POSITIVE LOGITS
     Rough
    1.13
     rough
    1.07
    Rough
    0.99
     roughness
    0.90
    rough
    0.88
    ghest
    0.85
     Tough
    0.73
    Tough
    0.68
     tough
    0.66
    tough
    0.66
    Activations Density 0.005%

    No Known Activations