© 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. 35-GEMMASCOPE-RES-16K
    11. 6399
    Prev
    Next
    INDEX
    Explanations

    code elements related to methods and functions in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    架
    -0.28
     tongue
    -0.25
    اث
    -0.25
     Arxivat
    -0.25
     предполага
    -0.25
     bur
    -0.25
     suck
    -0.24
     pok
    -0.24
     основан
    -0.23
    ungsver
    -0.23
    POSITIVE LOGITS
     Getter
    0.90
     getter
    0.87
     ModelExpression
    0.82
    getter
    0.81
     getters
    0.81
    getters
    0.77
     accessor
    0.75
    Getter
    0.75
     AssemblyTitle
    0.71
     Gets
    0.71
    Activations Density 0.241%

    No Known Activations