© 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. 41-GEMMASCOPE-RES-16K
    11. 6990
    Prev
    Next
    INDEX
    Explanations

    elements related to significant entities, events, or concepts in various contexts

    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
     gauges
    -0.40
     gu
    -0.40
     Gu
    -0.39
     Guild
    -0.38
     Gau
    -0.38
    Gu
    -0.37
    gu
    -0.36
    ギ
    -0.36
     guild
    -0.36
     guil
    -0.35
    POSITIVE LOGITS
     Gra
    2.42
     gra
    2.36
    Gra
    2.31
    gra
    2.16
     GRA
    2.11
     GR
    2.11
    GR
    1.96
    GRA
    1.94
     gr
    1.93
     Gr
    1.91
    Activations Density 3.300%

    No Known Activations