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

    Neuronpedia

    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. 31-GEMMASCOPE-RES-16K
    11. 8083
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to requests and denials in a judicial context

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

    legal documents containing formal requests and denials of access or privileges.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SuspendLayout
    -0.43
    发表于
    -0.37
    
    -0.36
    ViewImports
    -0.36
     utom
    -0.34
    printStackTrace
    -0.33
    ティブ
    -0.32
    tiftung
    -0.31
    hafter
    -0.31
    iliary
    -0.30
    POSITIVE LOGITS
     request
    3.06
     requests
    2.80
     requesting
    2.66
     requested
    2.52
     Request
    2.47
     REQUEST
    2.41
     Requests
    2.38
    request
    2.33
    Request
    2.14
     Requested
    2.11
    Activations Density 1.112%

    No Known Activations