© 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. 36-GEMMASCOPE-RES-16K
    11. 8205
    Prev
    Next
    INDEX
    Explanations

    important aspects, issues, or factors within various contexts, particularly related to analysis and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     convenable
    -0.37
    mappedBy
    -0.36
    只能
    -0.33
    cemment
    -0.33
    Morfo
    -0.33
     столько
    -0.32
     alguma
    -0.32
    也只能
    -0.32
     aquele
    -0.32
    ideae
    -0.31
    POSITIVE LOGITS
     worth
    0.75
    需要注意
    0.75
     overlooked
    0.75
    tagHelperRunner
    0.72
     missing
    0.69
     besides
    0.66
     noteworthy
    0.65
     diperhatikan
    0.65
     important
    0.63
     omitted
    0.60
    Activations Density 0.734%

    No Known Activations