© 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. 525
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to velocity and its conversions in programming

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

    unit conversions from text

    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
     Husbandry
    -0.35
    苷
    -0.32
    charpe
    -0.32
     wilds
    -0.31
     OMITTED
    -0.31
    ลำ
    -0.31
     armados
    -0.30
     joaat
    -0.30
     wild
    -0.30
    互
    -0.30
    POSITIVE LOGITS
    RTHOOK
    0.58
     snippetHide
    0.53
    writeFieldEnd
    0.52
    ➯
    0.50
    migrationBuilder
    0.49
    RTEE
    0.49
    HasAnnotation
    0.48
    цездатний
    0.48
    cair
    0.48
     informée
    0.48
    Activations Density 0.009%

    No Known Activations