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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1473
    Prev
    Next
    INDEX
    Explanations

    terms related to legal actions and requests for permission within a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Requests for permission or authorization

    np_acts-logits-general · gemini-2.0-flash

    permission to abandon or file

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    嫌
    -0.33
    gg
    -0.30
     dist
    -0.29
     universal
    -0.29
    xi
    -0.29
    燕
    -0.29
     Tack
    -0.29
     propOrder
    -0.28
    انتهای
    -0.28
    FirebaseUser
    -0.28
    POSITIVE LOGITS
     permission
    0.68
     Permission
    0.63
    IVEREF
    0.63
     permit
    0.59
     permits
    0.58
     permissions
    0.58
    permission
    0.57
     requests
    0.57
     Permissions
    0.57
    permit
    0.57
    Activations Density 0.395%

    No Known Activations