© 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
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 69
    Prev
    Next
    INDEX
    Explanations

    words related to CURative properties and actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reason
    -0.37
     reason
    -0.36
     pretty
    -0.35
    Reason
    -0.34
     Bad
    -0.34
     Seguro
    -0.34
    hnung
    -0.33
     Schutz
    -0.32
     Fol
    -0.32
    ть
    -0.32
    POSITIVE LOGITS
     CUR
    0.76
     cur
    0.75
    cur
    0.75
     Cur
    0.75
    Cur
    0.70
    httphttps
    0.64
    CUR
    0.64
    AutoField
    0.61
     kur
    0.60
    Kur
    0.60
    Activations Density 0.163%

    No Known Activations