© 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. 9-GEMMASCOPE-RES-131K
    11. 31269
    Prev
    Next
    INDEX
    Explanations

    contextual references to specific needs and preferences of individuals in various situations

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

    suit preferences or needs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.52
     nahilalakip
    -0.44
    */].
    -0.43
    EDEFAULT
    -0.43
    chieht
    -0.39
     chi̍t
    -0.38
    jstor
    -0.37
    classnames
    -0.36
     ác
    -0.36
    terminal
    -0.35
    POSITIVE LOGITS
     adapt
    0.47
    ukone
    0.46
     adapted
    0.46
     adapting
    0.46
    setVerticalGroup
    0.43
     typelib
    0.42
     adapts
    0.41
     ujednoznacz
    0.41
     adaptarse
    0.41
     Wikimedijinoj
    0.40
    Activations Density 0.100%

    No Known Activations