© 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. 41-GEMMASCOPE-RES-16K
    11. 10502
    Prev
    Next
    INDEX
    Explanations

    references to specific characters or entities in a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    е
    -0.89
    ere
    -0.85
    ea
    -0.85
    e
    -0.84
    eb
    -0.84
    ez
    -0.84
    eh
    -0.83
    ec
    -0.82
    es
    -0.82
    ej
    -0.81
    POSITIVE LOGITS
    accompagnement
    0.37
    assemblée
    0.32
    migrationBuilder
    0.30
    ucoup
    0.29
    urra
    0.29
    aménagement
    0.28
    uacute
    0.28
    odic
    0.27
    ocirc
    0.27
    hoga
    0.26
    Activations Density 2.178%

    No Known Activations