© 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. 1366
    Prev
    Next
    INDEX
    Explanations

    key elements related to sports leagues and their associated media

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

    virus infectivity installation lawyer

    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
     بر
    -0.26
     Tujuan
    -0.25
     para
    -0.25
    Span
    -0.25
     yö
    -0.25
     term
    -0.24
     base
    -0.24
     гро
    -0.24
     key
    -0.24
     fishing
    -0.24
    POSITIVE LOGITS
     betweenstory
    0.94
    RegressionTest
    0.88
    rungsseite
    0.83
    IndentedString
    0.81
    AndEndTag
    0.80
    tagHelperRunner
    0.77
    évaluateur
    0.75
    ConstraintMaker
    0.74
    InjectAttribute
    0.74
    нгред
    0.73
    Activations Density 0.038%

    No Known Activations