© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 13413
    Prev
    Next
    INDEX
    Explanations

    syntax and structure related to programming and code formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.65
     تضيفلها
    -0.61
    /**
    -0.59
    Revenir
    -0.52
    pecabe
    -0.50
     autorytatywna
    -0.49
     invokingState
    -0.49
    formik
    -0.48
     виправивши
    -0.48
     étoient
    -0.47
    POSITIVE LOGITS
    ↵↵↵
    1.20
    ↵↵↵↵
    0.72
    ↵↵↵↵↵
    0.63
     \\
    0.53
    ↵↵↵↵↵↵
    0.51
    </h4>
    0.50
    </td>
    0.48
    ",$
    0.47
    </h2>
    0.46
    例文帳に追加
    0.44
    Activations Density 0.151%

    No Known Activations