© 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. 39-GEMMASCOPE-RES-16K
    6. 3148
    Prev
    Next
    INDEX
    Explanations

    terms related to governance, legal issues, and structured organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pretty
    -0.42
     is
    -0.34
     desped
    -0.31
     Hay
    -0.30
     face
    -0.30
    Hay
    -0.30
     (
    -0.30
     hin
    -0.30
    现
    -0.29
     cas
    -0.29
    POSITIVE LOGITS
     للمعارف
    0.83
    〮
    0.83
     MainAxisSize
    0.81
    ſchaft
    0.74
     endblock
    0.70
     betweenstory
    0.66
    majánló
    0.66
     stockbild
    0.65
     queſta
    0.65
     الحره
    0.64
    Activations Density 0.438%

    No Known Activations