© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 12099
    Prev
    Next
    INDEX
    Explanations

    code comments and documentation indicators

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

    code comments and remote operations

    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
    ⏟
    -0.40
     concern
    -0.34
    ことです
    -0.34
    krie
    -0.33
     Geraadpleegd
    -0.32
     faltan
    -0.32
     consultato
    -0.31
     useStyles
    -0.31
    sproz
    -0.31
     Arkivert
    -0.30
    POSITIVE LOGITS
    TacToe
    0.59
    TagMode
    0.58
    AndEndTag
    0.57
     चीज़ों
    0.56
     <>",
    0.56
    tagHelperRunner
    0.51
    OGND
    0.51
    RTLR
    0.50
    期刊论文
    0.50
    iastes
    0.50
    Activations Density 0.004%

    No Known Activations