Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 82997
    Prev
    Next
    INDEX
    Explanations

    specific names or identifiers related to people or entities

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

    artichokes, done, forward

    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
    tanleria
    -0.52
    tagHelperRunner
    -0.51
     Taktlose
    -0.51
     שוליים
    -0.47
    WebElementEntity
    -0.42
    setof
    -0.42
    солю
    -0.42
     MotionEvent
    -0.42
    trun
    -0.40
    पया
    -0.40
    POSITIVE LOGITS
     propOrder
    0.45
    ViewImports
    0.43
    setVerticalGroup
    0.43
    chartInstance
    0.43
     himself
    0.43
    Serde
    0.42
    học
    0.40
     phonetic
    0.40
     StatelessWidget
    0.40
    tagHelper
    0.40
    Activations Density 0.005%

    No Known Activations