© 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. 63636
    Prev
    Next
    INDEX
    Explanations

    names of specific athletes and their associated actions or performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     contextLoads
    -0.38
    binaan
    -0.36
    SpringRunner
    -0.35
     amounts
    -0.34
     nahilalakip
    -0.34
    ResponseWriter
    -0.33
     letters
    -0.33
     bordada
    -0.33
    注重
    -0.32
    
    -0.31
    POSITIVE LOGITS
    himovic
    0.63
    webElement
    0.47
    webElementGuid
    0.47
    utang
    0.47
     يتيمه
    0.47
     chipping
    0.47
    trooper
    0.47
    maiden
    0.47
    UrlEncoded
    0.47
    ⎈
    0.46
    Activations Density 0.007%

    No Known Activations