© 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. 38-GEMMASCOPE-RES-16K
    11. 12759
    Prev
    Next
    INDEX
    Explanations

    specific information related to quantities, measurements, and actions associated with content management and user interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ispiel
    -0.38
    
    -0.35
    ettare
    -0.35
    imakasih
    -0.34
     précédents
    -0.32
    Again
    -0.32
    tilhar
    -0.32
     foregoing
    -0.31
     будем
    -0.31
    alors
    -0.31
    POSITIVE LOGITS
     once
    4.41
    once
    3.78
    Once
    3.58
     Once
    3.58
     ONCE
    3.09
    ONCE
    2.89
     einmal
    2.45
    一旦
    2.38
     sekali
    2.23
    一度
    2.11
    Activations Density 1.119%

    No Known Activations