© 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. 36-GEMMASCOPE-RES-16K
    11. 15918
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contrast or contradiction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     therefore
    -0.99
     sice
    -0.95
    therefore
    -0.88
     zwar
    -0.82
    indeed
    -0.79
    Therefore
    -0.76
     indeed
    -0.75
     infatti
    -0.73
     Therefore
    -0.71
     certes
    -0.71
    POSITIVE LOGITS
     cautioned
    0.67
     cautions
    0.66
     beware
    0.61
     caution
    0.60
     tetap
    0.59
     caveat
    0.58
     caveats
    0.58
     ultimately
    0.56
    卻
    0.56
     samtidig
    0.56
    Activations Density 0.759%

    No Known Activations