© 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. 21-GEMMASCOPE-RES-16K
    11. 3204
    Prev
    Next
    INDEX
    Explanations

    references to family relationships, specifically the titles "Jr" and "Sr."

    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
    óta
    -0.37
    牛
    -0.29
    WHE
    -0.28
     rolling
    -0.28
     ot
    -0.27
    })));
    -0.27
     betre
    -0.27
     bumbu
    -0.27
    👍👍
    -0.26
     Hör
    -0.26
    POSITIVE LOGITS
    VIAF
    0.77
     Exactos
    0.69
    ⓧ
    0.68
     utafitiHapana
    0.66
     arşivlendi
    0.66
    ContentAsync
    0.66
    SharedCtor
    0.65
    ImageContext
    0.65
    +#+
    0.64
    istoitu
    0.64
    Activations Density 0.131%

    No Known Activations