© 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. 12917
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and logical expressions

    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
    RTLR
    -0.62
     betweenstory
    -0.60
    EDEFAULT
    -0.59
    Hentet
    -0.56
    outSlope
    -0.56
     Réponses
    -0.54
     ModelRenderer
    -0.52
     ProtoMessage
    -0.51
    parsedMessage
    -0.51
    MarshalTo
    -0.50
    POSITIVE LOGITS
    unfinished
    0.54
     intermediate
    0.33
    ungen
    0.33
    intellij
    0.33
     Newell
    0.32
     continúas
    0.31
     advanced
    0.31
     extended
    0.30
     constru
    0.29
    AndEndTag
    0.29
    Activations Density 0.436%

    No Known Activations