© 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. 21803
    Prev
    Next
    INDEX
    Explanations

    elements indicative of a structured or logical decision-making process

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

    user input and code

    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
     limit
    -0.32
     no
    -0.31
     some
    -0.30
    简
    -0.27
     excited
    -0.27
     hard
    -0.27
     increased
    -0.27
     par
    -0.26
    Surviving
    -0.26
     acceleration
    -0.25
    POSITIVE LOGITS
    IndentedString
    0.77
     zuſammen
    0.75
    IsContent
    0.74
    RectangleBorder
    0.73
     الرياضيه
    0.72
     queſta
    0.72
    下载附件
    0.71
    GraphicsUnit
    0.70
    NameInMap
    0.70
     nakalista
    0.70
    Activations Density 0.030%

    No Known Activations