© 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. 21-GEMMASCOPE-RES-16K
    11. 13965
    Prev
    Next
    INDEX
    Explanations

    descriptions and actions related to military or combat scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/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.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stdc
    -0.46
     Foire
    -0.33
     mate
    -0.33
    CodedInputStream
    -0.32
    IGENCE
    -0.32
    ServletException
    -0.31
     Cb
    -0.30
    Chel
    -0.29
    Française
    -0.29
    ↵↵
    -0.29
    POSITIVE LOGITS
    KommentareTeilen
    0.66
     հղումներ
    0.61
     kasarigan
    0.60
    expandindo
    0.60
     pinulongan
    0.57
     فريبيس
    0.56
     يتيمه
    0.54
    Gambas
    0.53
    tagPool
    0.52
    RenderAtEndOf
    0.51
    Activations Density 0.733%

    No Known Activations