© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-GEMMASCOPE-RES-16K
    11. 10678
    Prev
    Next
    INDEX
    Explanations

    references to education, training, and conditioning related to behavior and societal beliefs

    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
     protoimpl
    -0.64
    󠁴
    -0.54
     AssemblyCulture
    -0.54
     betweenstory
    -0.52
    IsMutable
    -0.52
     stiefe
    -0.48
    onedDateTime
    -0.48
    Diweddarwch
    -0.47
    tagHelperRunner
    -0.46
    intendent
    -0.45
    POSITIVE LOGITS
     Taught
    0.71
     taught
    0.71
     Trained
    0.66
    taught
    0.64
     trained
    0.64
     indoctr
    0.63
    trained
    0.59
     Teach
    0.59
     teach
    0.58
    Trained
    0.58
    Activations Density 0.380%

    No Known Activations