© 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. 37-GEMMASCOPE-RES-16K
    11. 1997
    Prev
    Next
    INDEX
    Explanations

    negations and expressions of refusal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    correctly
    -0.58
     bastante
    -0.52
     claramente
    -0.52
     suitably
    -0.51
     correctly
    -0.51
    plenty
    -0.51
    successfully
    -0.49
     ziemlich
    -0.48
     מאוד
    -0.48
     appropriately
    -0.47
    POSITIVE LOGITS
     waste
    0.74
     wasting
    0.73
     jeopardize
    0.63
     risk
    0.60
     jeopardi
    0.59
     burden
    0.58
     bother
    0.57
     WASTE
    0.56
     risking
    0.56
     interfere
    0.56
    Activations Density 0.626%

    No Known Activations