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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 8428
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and acknowledgment in professional contexts

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

    years of service

    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
    asko
    -0.36
    ülő
    -0.34
     Koz
    -0.34
     Kan
    -0.34
     cake
    -0.33
     babi
    -0.32
    tualmente
    -0.32
    эффици
    -0.32
     Currently
    -0.32
     kom
    -0.32
    POSITIVE LOGITS
    Autoritní
    0.73
    ftagPool
    0.51
     كومونز
    0.50
    évaluateur
    0.50
    ésultats
    0.49
     ThemeData
    0.49
     manqué
    0.49
    writeFieldEnd
    0.45
     Obrador
    0.45
     disambiguazione
    0.45
    Activations Density 0.010%

    No Known Activations