© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8923
    Prev
    Next
    INDEX
    Explanations

    terms related to dimensions and constraints in a graphical or data representation context

    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
     decoration
    -0.46
    #
    -0.44
    endregion
    -0.43
    Aval
    -0.43
    /*
    -0.42
    hall
    -0.41
    conte
    -0.41
     documentaries
    -0.40
     OA
    -0.40
     crus
    -0.40
    POSITIVE LOGITS
     max
    1.16
     adequately
    1.12
     properly
    1.08
     maximum
    1.02
     maximal
    1.02
     adecuadamente
    0.98
     correctly
    0.98
    MAX
    0.97
     appropriately
    0.97
    Max
    0.97
    Activations Density 0.234%

    No Known Activations