© 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. 20-GEMMASCOPE-RES-16K
    11. 11701
    Prev
    Next
    INDEX
    Explanations

    textual references or annotations in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     isEmpty
    -0.52
    russian
    -0.49
     pelúcia
    -0.48
    isSuccess
    -0.46
     Egli
    -0.45
     Imm
    -0.45
     Trasp
    -0.44
    isEmpty
    -0.43
    employer
    -0.43
    Dlaczego
    -0.43
    POSITIVE LOGITS
     note
    1.27
     Notes
    1.20
     Note
    1.20
     notes
    1.16
    Note
    1.13
    note
    1.10
    Notes
    1.09
     NOTES
    1.03
    notes
    1.02
     NOTE
    0.97
    Activations Density 0.096%

    No Known Activations