© 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. 11-GEMMASCOPE-RES-16K
    11. 10506
    Prev
    Next
    INDEX
    Explanations

    references to the existence and actions of entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TC
    -0.31
    chartInstance
    -0.31
     gelegen
    -0.31
     colina
    -0.30
     lernen
    -0.30
     zvlá
    -0.30
    imetric
    -0.29
     especially
    -0.29
     capable
    -0.29
    <table>
    -0.29
    POSITIVE LOGITS
     يتيمه
    0.75
    hoeddwyd
    0.69
    elemField
    0.68
    StoryboardSegue
    0.67
    bitField
    0.67
    IsMutable
    0.62
    oa̍t
    0.60
    tanleria
    0.59
     незавершена
    0.59
    WriteTagHelper
    0.57
    Activations Density 1.498%

    No Known Activations