© 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. 42327
    Prev
    Next
    INDEX
    Explanations

    terms related to measurements, evaluations, and results in a quantitative context

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

    actual circumstances may differ

    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
    complexContent
    -0.70
    
    -0.54
    specially
    -0.52
     grundsätzlich
    -0.52
     traditionally
    -0.51
     algemeen
    -0.51
     PeEnEo
    -0.51
     Biôgrafia
    -0.51
     generell
    -0.50
     generally
    -0.50
    POSITIVE LOGITS
     bây
    0.46
    わけではない
    0.44
     dopiero
    0.39
     sebenar
    0.39
     differs
    0.39
    还得
    0.37
     Actually
    0.37
    훨
    0.36
     deviate
    0.36
    分からない
    0.35
    Activations Density 0.114%

    No Known Activations