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

    Neuronpedia

    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. 23-GEMMASCOPE-RES-16K
    11. 2271
    Prev
    Next
    INDEX
    Explanations

    instances of specific names and associated identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cejas
    -0.77
     rantai
    -0.75
     almohada
    -0.74
     sorpresas
    -0.73
     ladrillo
    -0.71
     desmotivaciones
    -0.70
     manguera
    -0.70
     agujas
    -0.69
     rajut
    -0.69
     botellas
    -0.68
    POSITIVE LOGITS
     Y
    0.79
     N
    0.78
     H
    0.78
     D
    0.77
     V
    0.77
     Z
    0.76
     G
    0.76
     B
    0.75
     K
    0.75
     M
    0.75
    Activations Density 0.769%

    No Known Activations