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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 105482
    Prev
    Next
    INDEX
    Explanations

    instances of the word "leave" and its variants in various contexts

    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
     Inscrivez
    -0.48
    mapStateToProps
    -0.46
     deleteById
    -0.43
    typeorm
    -0.43
    djangoproject
    -0.42
     miroir
    -0.42
     espet
    -0.41
    ViewFeatures
    -0.41
     taas
    -0.41
     uyar
    -0.41
    POSITIVE LOGITS
     Leave
    0.98
     leave
    0.93
    Leave
    0.92
    leave
    0.85
     Leaving
    0.84
     leaving
    0.82
    Leaving
    0.79
     LEAVE
    0.75
    leaving
    0.73
    LEAVE
    0.69
    Activations Density 0.026%

    No Known Activations