© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 6652
    Prev
    Next
    INDEX
    Explanations

    instances of the word "said" 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 @ 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
     للاسماء
    -0.69
    migrationBuilder
    -0.67
     Савезне
    -0.66
     jsPsych
    -0.57
    addCriterion
    -0.57
     zuſammen
    -0.55
     queſta
    -0.55
     pleaſure
    -0.55
     faſt
    -0.55
    LLocation
    -0.55
    POSITIVE LOGITS
     a
    0.52
     the
    0.50
     said
    0.46
     my
    0.42
     by
    0.42
     oleh
    0.38
     Silber
    0.37
     our
    0.36
     an
    0.36
     de
    0.35
    Activations Density 0.078%

    No Known Activations