© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 53260
    Prev
    Next
    INDEX
    Explanations

    elements related to battles against evil forces

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

    sentences or phrases describing narrative action or plot events (conflict, heroes/villains, and story progression).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     tartalomajánló
    -0.58
    Kaynakça
    -0.57
     pinulongan
    -0.56
     Wiktionnaire
    -0.52
    createCanvas
    -0.51
     Masyarakat
    -0.49
     invokingState
    -0.49
    География
    -0.49
    
    -0.48
    المناصب
    -0.47
    POSITIVE LOGITS
    ronpa
    0.58
     propOrder
    0.39
    ByPrimaryKey
    0.37
     PeEnEo
    0.37
     mergeFrom
    0.36
     surla
    0.35
    nath
    0.35
     wind
    0.34
    </h5>
    0.34
     ')[
    0.34
    Activations Density 0.135%

    No Known Activations