© 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. 20-GEMMASCOPE-RES-131K
    11. 92966
    Prev
    Next
    INDEX
    Explanations

    technical terms related to object manipulation and memory management in programming

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

    unless otherwise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .*")]
    -0.62
     للمعارف
    -0.57
     للاسماء
    -0.56
     lenker
    -0.55
    الحياه
    -0.54
    ViewFeatures
    -0.53
     Administrativna
    -0.52
    LookAnd
    -0.52
     Infórmanos
    -0.52
    urka
    -0.52
    POSITIVE LOGITS
     unless
    0.43
     jinak
    0.36
     otherwise
    0.35
     spørgsmål
    0.33
    unless
    0.33
     unlike
    0.30
     contraire
    0.30
    этому
    0.29
     természetes
    0.29
     żad
    0.28
    Activations Density 0.068%

    No Known Activations