© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 12868
    Prev
    Next
    INDEX
    Explanations

    instances of violence or abusive behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     misiones
    -0.41
     trữ
    -0.41
     plán
    -0.40
    úsqueda
    -0.40
     resources
    -0.40
     Vermögen
    -0.39
     cesty
    -0.39
    complexType
    -0.38
    visionnement
    -0.38
     Sicherung
    -0.37
    POSITIVE LOGITS
     beat
    0.67
    beat
    0.66
     punches
    0.64
     BEAT
    0.63
    httphttps
    0.60
     Beat
    0.60
     beating
    0.59
     beaten
    0.58
     ضرب
    0.58
     beats
    0.57
    Activations Density 0.420%

    No Known Activations