© 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. 73927
    Prev
    Next
    INDEX
    Explanations

    references to extended durations of time or lengthy periods

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

    long duration or time periods

    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
    rush
    -0.43
     rush
    -0.42
    cloudf
    -0.38
     sharp
    -0.38
    gol
    -0.37
    voo
    -0.36
    strict
    -0.35
     rapides
    -0.35
    Fris
    -0.35
    cris
    -0.35
    POSITIVE LOGITS
     prolonged
    0.75
     longest
    0.73
     lâu
    0.72
     long
    0.69
    longest
    0.68
     lengthy
    0.67
     longtemps
    0.67
     dlouho
    0.67
     protracted
    0.65
     longa
    0.65
    Activations Density 0.211%

    No Known Activations