© 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. 20-GEMMASCOPE-RES-131K
    6. 95989
    Prev
    Next
    INDEX
    Explanations

    categories related to film and awards

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

    Entities with parentheses

    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
     lateinit
    -0.35
    Geplaatst
    -0.35
    lateinit
    -0.34
    HttpPut
    -0.33
     comuniques
    -0.33
     ivelany
    -0.33
    bParam
    -0.33
    
    -0.32
    点此举报
    -0.32
     հղումներ
    -0.31
    POSITIVE LOGITS
    RegistryLite
    0.55
    PointerException
    0.54
    potranspiration
    0.53
    mogorov
    0.51
    MethodManager
    0.49
    TargetException
    0.49
    ➋
    0.49
    tanooga
    0.48
    StreetMap
    0.48
    OCCURRED
    0.48
    Activations Density 0.063%

    No Known Activations