© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 35073
    Prev
    Next
    INDEX
    Explanations

    instances of the abbreviation "sm" and its variations, often related to specific technical or programming contexts, highlights its emphasis on monitoring system performance

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

    sm and following tokens

    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
    NewUrlParser
    -0.56
    argout
    -0.54
    Voltaje
    -0.54
    GetAxis
    -0.52
    Acceso
    -0.52
     prestaciones
    -0.52
     nevera
    -0.51
     ユーザー
    -0.49
    RequestQueue
    -0.49
     getPath
    -0.49
    POSITIVE LOGITS
     SM
    1.02
     Sm
    1.02
    SM
    0.92
    Sm
    0.91
     sm
    0.85
    sm
    0.80
     Smal
    0.77
     SMC
    0.74
     Smar
    0.74
     Smyth
    0.73
    Activations Density 0.031%

    No Known Activations