© 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. 37-GEMMASCOPE-RES-16K
    11. 4777
    Prev
    Next
    INDEX
    Explanations

    references to physics-related content and terms

    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
    Personendaten
    -0.71
    TagMode
    -0.69
    rungsseite
    -0.62
    Reduction
    -0.60
     مواليد
    -0.60
     informée
    -0.59
    reduction
    -0.57
     Returned
    -0.57
     Responses
    -0.57
     Reactions
    -0.57
    POSITIVE LOGITS
     RE
    0.98
     ré
    0.96
     ре
    0.92
     rep
    0.81
    Ре
    0.77
    RE
    0.76
     Ré
    0.74
    レ
    0.68
     Ре
    0.68
    ре
    0.68
    Activations Density 1.388%

    No Known Activations