© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 14243
    Prev
    Next
    INDEX
    Explanations

    phrases or contexts involving denial or rejection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HALL
    -0.50
     utafitiHapana
    -0.50
    omiast
    -0.49
    WithEmail
    -0.49
     infine
    -0.48
    Abp
    -0.48
    inafter
    -0.47
     indisponible
    -0.47
    (||
    -0.46
    先是
    -0.46
    POSITIVE LOGITS
     exactly
    0.93
     even
    0.86
     bother
    0.81
     necessarily
    0.81
     really
    0.81
    exactly
    0.81
     exatamente
    0.77
     much
    0.73
     minded
    0.72
    necessarily
    0.72
    Activations Density 0.349%

    No Known Activations