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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 108319
    Prev
    Next
    INDEX
    Explanations

    mentions of temporary or impermanent situations

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

    temporary or short-term

    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
     nahilalakip
    -0.49
     peuples
    -0.45
     productivo
    -0.44
     pantalón
    -0.42
     biens
    -0.42
     huvud
    -0.41
     Económica
    -0.39
     naturligt
    -0.39
     canadien
    -0.38
     principaux
    -0.37
    POSITIVE LOGITS
     temporary
    0.77
     ephemeral
    0.75
    temporary
    0.73
     makeshift
    0.73
     Temporary
    0.73
     improvis
    0.68
     improvised
    0.67
    Temporary
    0.67
     flash
    0.62
     transient
    0.62
    Activations Density 0.009%

    No Known Activations