© 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. 0-GEMMASCOPE-RES-16K
    11. 10590
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "release" 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 @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eindruck
    -0.49
     Volkes
    -0.48
    +#+
    -0.43
     Schülerinnen
    -0.42
     Wortes
    -0.40
     Menschheit
    -0.39
     취
    -0.37
     Reihe
    -0.37
     parcela
    -0.36
     colonnes
    -0.36
    POSITIVE LOGITS
    Something
    0.91
     release
    0.86
     Something
    0.84
    something
    0.82
     Release
    0.70
     something
    0.69
    released
    0.68
     RELEASE
    0.68
    release
    0.67
     released
    0.66
    Activations Density 0.426%

    No Known Activations