© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 102626
    Prev
    Next
    INDEX
    Explanations

    terms and expressions related to viability and viral entities, particularly associated with Vienna and related research contexts

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

    vi- words and Vienna

    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
    Schul
    -0.56
    $_['
    -0.51
    IntoConstraints
    -0.50
     Harder
    -0.50
    tley
    -0.50
    oney
    -0.49
    Ể
    -0.49
    setLength
    -0.48
    don
    -0.48
    cker
    -0.48
    POSITIVE LOGITS
    VIAF
    0.98
     Vi
    0.78
     Viability
    0.78
    Vi
    0.78
     VI
    0.77
     Vibe
    0.74
    Vig
    0.68
    VI
    0.68
     vi
    0.68
     Vivian
    0.66
    Activations Density 0.015%

    No Known Activations