© 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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105729
    Prev
    Next
    INDEX
    Explanations

    elements related to digital interaction and hyperlinks

    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
    thâu
    -0.59
    Życiorys
    -0.50
     Taktlose
    -0.47
    хьтан
    -0.47
    पया
    -0.46
    忑
    -0.45
    Toponymie
    -0.45
     Chwiliwch
    -0.44
    embatan
    -0.44
     Crusoe
    -0.44
    POSITIVE LOGITS
     defaultstate
    0.73
    AsUp
    0.47
    windowFixed
    0.45
    LookAnd
    0.42
     CanadaChoose
    0.42
     '\\;'
    0.42
    InjectAttribute
    0.40
    GEBURTSDATUM
    0.38
     platy
    0.35
     tilbud
    0.35
    Activations Density 0.374%

    No Known Activations