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

    Neuronpedia

    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. 12-GEMMASCOPE-RES-16K
    11. 6441
    Prev
    Next
    INDEX
    Explanations

    negative expressions or phrases indicating negation or refusal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.45
    CardHeader
    -0.36
    ヮ
    -0.35
     δ
    -0.33
     kept
    -0.30
     Erfurt
    -0.30
    락
    -0.30
     pio
    -0.30
    Journal
    -0.29
    Glee
    -0.29
    POSITIVE LOGITS
     utafitiHapana
    0.70
    jména
    0.66
     bukanlah
    0.66
     miniaturka
    0.66
     indígen
    0.65
    並不是
    0.65
    ########.
    0.65
     estadounid
    0.64
    ágenes
    0.64
     meille
    0.63
    Activations Density 0.266%

    No Known Activations