© 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. 1-GEMMASCOPE-RES-16K
    11. 8285
    Prev
    Next
    INDEX
    Explanations

    negative or opposing sentiments and phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -
    -0.52
    ‐
    -0.37
    页面存档备份
    -0.33
    Londres
    -0.33
    zeiti
    -0.30
     Melayu
    -0.30
    niczka
    -0.30
     Moskau
    -0.29
     Andalucía
    -0.29
     betwixt
    -0.28
    POSITIVE LOGITS
    <bos>
    1.19
     the
    0.70
     ſehr
    0.69
     ſondern
    0.65
    <unused52>
    0.63
    <unused21>
    0.63
    [@BOS@]
    0.63
    ྑ
    0.63
    <unused68>
    0.63
    <unused14>
    0.63
    Activations Density 0.688%

    No Known Activations