© 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. 38-GEMMASCOPE-RES-16K
    11. 13553
    Prev
    Next
    INDEX
    Explanations

    dialogues involving expressions of emotion or reactions between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CanadaChoose
    -0.48
     للمعارف
    -0.47
     excited
    -0.46
     giggling
    -0.46
    Vidite
    -0.45
    Excited
    -0.45
     Excited
    -0.44
     Bewußt
    -0.44
     geluk
    -0.44
     delighted
    -0.43
    POSITIVE LOGITS
     rubbed
    0.68
     scratched
    0.63
     shrugged
    0.57
     rubs
    0.56
     scratch
    0.55
     rub
    0.55
     shook
    0.55
     chewed
    0.55
     shake
    0.54
     scratching
    0.54
    Activations Density 0.152%

    No Known Activations