© 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. 21-GEMMASCOPE-RES-16K
    11. 12877
    Prev
    Next
    INDEX
    Explanations

    references to race and implications of racial identity or issues

    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
    TemporalType
    -0.58
    CppMethod
    -0.57
    KommentareTeilen
    -0.54
    LLocation
    -0.53
    WebElementEntity
    -0.51
     AspNetCore
    -0.50
    IsMutable
    -0.50
     forState
    -0.49
     NSError
    -0.49
     jLabel
    -0.47
    POSITIVE LOGITS
     Damit
    0.42
     mierda
    0.42
    atnya
    0.42
     nonUne
    0.41
    ceği
    0.40
     trampa
    0.40
     νο
    0.40
     risa
    0.38
     bullshit
    0.38
    kező
    0.38
    Activations Density 0.667%

    No Known Activations