© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 13401
    Prev
    Next
    INDEX
    Explanations

    references to significant quantities and their effects in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.68
    __":
    -0.54
    slightly
    -0.51
    Slightly
    -0.51
     slightly
    -0.50
     Slightly
    -0.50
     extremely
    -0.49
    ❸
    -0.48
    全然
    -0.47
     somehow
    -0.47
    POSITIVE LOGITS
     amount
    0.95
     amounts
    0.83
    amount
    0.76
     emphasis
    0.71
    amounts
    0.69
     degree
    0.66
    emphasis
    0.59
     Amounts
    0.58
     sekali
    0.57
     overlap
    0.57
    Activations Density 0.747%

    No Known Activations