© 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. 10-GEMMASCOPE-RES-16K
    11. 11338
    Prev
    Next
    INDEX
    Explanations

    discussions about volunteer work and charitable involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     morire
    -0.39
     often
    -0.38
     îns
    -0.37
    HasColumnName
    -0.37
     Indeed
    -0.37
    escens
    -0.37
     Th
    -0.36
     Näch
    -0.36
     Verarbeitung
    -0.35
     jed
    -0.35
    POSITIVE LOGITS
     ویکی‌پدی
    0.68
     <<<<<<<<<<<<<<
    0.65
    лтемелер
    0.54
     صوتيه
    0.51
    новниш
    0.49
    ConstraintMaker
    0.49
    RTSN
    0.49
    +#+
    0.49
     transfieras
    0.48
    MarshalTo
    0.47
    Activations Density 0.849%

    No Known Activations