© 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. 99764
    Prev
    Next
    INDEX
    Explanations

    mention of empirical methods and models in scientific contexts

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

    empirical models and descriptions

    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
    ChildScrollView
    -0.47
     bav
    -0.44
    IntoConstraints
    -0.44
    zette
    -0.38
     LMS
    -0.38
     condi
    -0.35
     textbook
    -0.35
     Barra
    -0.35
     chal
    -0.35
    новниш
    -0.35
    POSITIVE LOGITS
     linkovi
    0.51
     tocó
    0.50
     autoridad
    0.45
    AFFIRMED
    0.45
     autorité
    0.45
     autoridade
    0.44
     Preguntas
    0.44
     cucchia
    0.44
    Affirmed
    0.44
     Töchter
    0.43
    Activations Density 0.343%

    No Known Activations