© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 5511
    Prev
    Next
    INDEX
    Explanations

    emotional reactions and expressions of surprise or shock

    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
     yawn
    -0.52
     complain
    -0.52
     complained
    -0.46
     grumbled
    -0.45
     complaining
    -0.44
     yaw
    -0.41
     disappro
    -0.41
     chuckles
    -0.41
     complains
    -0.40
     fussy
    -0.40
    POSITIVE LOGITS
     desperately
    0.68
     praying
    0.67
     prayed
    0.67
    UnusedPrivate
    0.64
    Praying
    0.63
     desperation
    0.60
     pray
    0.59
     desperate
    0.58
     prays
    0.58
     willed
    0.56
    Activations Density 0.227%

    No Known Activations