© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104506
    Prev
    Next
    INDEX
    Explanations

    dates and numerical information, particularly years and copyright notices.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @subhashk

    instances of copyright information and references to licenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     مشين
    -0.47
    '&:
    -0.43
    optionalTypeArgs
    -0.41
    Sucesor
    -0.38
     Staub
    -0.37
    oredCriteria
    -0.37
     arrancar
    -0.37
    CROSSTALK
    -0.36
     Bestellung
    -0.36
    WindowListener
    -0.35
    POSITIVE LOGITS
    findpost
    0.60
    LookAnd
    0.56
    ViewImports
    0.54
     betweenstory
    0.48
    WH
    0.48
     Infórmanos
    0.47
    raisemb
    0.45
     lenker
    0.44
    müş
    0.44
    tadır
    0.43
    Activations Density 0.098%

    No Known Activations