© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 12939
    Prev
    Next
    INDEX
    Explanations

    expressions of strong negative sentiments or aversions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BorderRadius
    -0.64
    TintMode
    -0.63
    kema
    -0.58
     Rashford
    -0.54
     HasFactory
    -0.54
     للمعارف
    -0.52
    イビー
    -0.52
    ToolStripButton
    -0.51
    PDC
    -0.51
     })
    -0.50
    POSITIVE LOGITS
    Hate
    0.75
     Hate
    0.75
     Réponses
    0.73
     floats
    0.71
     hate
    0.69
    UIControlState
    0.67
    ony
    0.64
    hate
    0.63
     metav
    0.62
     kasarigan
    0.62
    Activations Density 0.077%

    No Known Activations