© 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 - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 65258
    Prev
    Next
    INDEX
    Explanations

    alphanumeric character sequences or identifiers

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

    hexadecimal UUID segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    oredCriteria
    -0.60
    󠁿
    -0.57
     gyhoeddwyd
    -0.57
    MessageOf
    -0.55
    +#+
    -0.54
    stdc
    -0.53
     Italijanski
    -0.51
     怎样
    -0.51
    ollectionView
    -0.51
     Chwiliwch
    -0.51
    POSITIVE LOGITS
    Kaynakça
    0.51
     Besøkt
    0.34
    useNewUrlParser
    0.32
    Eksteraj
    0.32
    writeField
    0.31
    romyalgia
    0.30
     المعيارى
    0.30
     navideña
    0.29
    SBATCH
    0.29
     useAuth
    0.28
    Activations Density 0.038%

    No Known Activations