© 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. 39-GEMMASCOPE-RES-16K
    11. 1243
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical and alphanumeric characters, indicating technical or coding content

    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
    pa
    -0.64
    b
    -0.64
    c
    -0.63
     b
    -0.62
    bs
    -0.62
    f
    -0.59
    ia
    -0.58
     c
    -0.58
    ib
    -0.58
    ma
    -0.57
    POSITIVE LOGITS
    E
    0.78
    C
    0.75
    D
    0.72
    F
    0.71
    FB
    0.68
    B
    0.67
    A
    0.64
    FD
    0.63
    SBATCH
    0.63
     getF
    0.62
    Activations Density 0.676%

    No Known Activations