© 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. 75598
    Prev
    Next
    INDEX
    Explanations

    references to notable films and their accolades or classifications

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

    years 2005 and 2006

    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
    nameof
    -0.51
     PeEnEo
    -0.50
    entyfik
    -0.44
     nonatomic
    -0.42
    instancetype
    -0.41
    ️
    -0.40
    DeleteBehavior
    -0.39
     bonté
    -0.39
    asyncio
    -0.39
     nameof
    -0.39
    POSITIVE LOGITS
     iPod
    0.71
     MySpace
    0.68
     XHTML
    0.66
    Vidite
    0.64
     DVDs
    0.63
     Sarkozy
    0.63
    lusconi
    0.61
    ulemon
    0.61
    OGND
    0.61
     Obama
    0.61
    Activations Density 0.781%

    No Known Activations