© 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. 4249
    Prev
    Next
    INDEX
    Explanations

    phrases expressing confirmation or validation in communication

    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
     صوتيه
    -0.46
     выйти
    -0.44
    ۣ
    -0.43
    ştır
    -0.39
     приве
    -0.39
    Demografie
    -0.39
     rápido
    -0.39
     blown
    -0.39
    congress
    -0.39
    Cyfeiriadau
    -0.39
    POSITIVE LOGITS
     himself
    0.85
    himself
    0.68
     Himself
    0.65
     był
    0.55
     psal
    0.53
     himſelf
    0.52
    他自己
    0.52
     stal
    0.51
     mógł
    0.50
     byl
    0.49
    Activations Density 0.036%

    No Known Activations