Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 24533
    Prev
    Next
    INDEX
    Explanations

    vulnerabilities and potential damages associated with mechanical devices and their protection measures

    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
    Affected
    -0.39
     afectado
    -0.39
     standen
    -0.38
    новниш
    -0.37
     kyllä
    -0.36
     Gastgeber
    -0.35
    antwoorde
    -0.35
     rechazo
    -0.34
     sén
    -0.34
    Principle
    -0.34
    POSITIVE LOGITS
    featureID
    0.54
    URLException
    0.51
    StackNavigator
    0.50
     فريبيس
    0.49
     accidents
    0.49
     Injury
    0.47
     bumps
    0.46
     injury
    0.46
    accident
    0.45
     crayons
    0.45
    Activations Density 0.055%

    No Known Activations