© 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. 10241
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their experiences or contributions

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

    who has been or did

    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
     accusing
    -0.36
     advirtió
    -0.35
     speculating
    -0.34
     announcing
    -0.34
    Collegamenti
    -0.34
     conceding
    -0.33
     blaming
    -0.32
     arguing
    -0.32
    ยว
    -0.32
     Beobach
    -0.32
    POSITIVE LOGITS
     exemplify
    0.73
     exemplifies
    0.66
     invokingState
    0.63
     getopt
    0.60
    ᅠ
    0.60
     distinguished
    0.60
     bravely
    0.59
    󠁿
    0.59
     exemp
    0.59
     embodies
    0.57
    Activations Density 0.031%

    No Known Activations