© 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 EvalsExportsinterp-engineNEWAPI 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. 10673
    Prev
    Next
    INDEX
    Explanations

    individuals' names and related biographical information

    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
     sisält
    -0.40
     mediano
    -0.39
     ewigen
    -0.39
     iNdEx
    -0.37
    OGND
    -0.36
     terbesar
    -0.34
     igång
    -0.34
     impossível
    -0.34
     vettoriale
    -0.34
     rápidos
    -0.34
    POSITIVE LOGITS
    -------------</
    0.55
    Gilla
    0.54
    ngths
    0.51
    */),
    0.48
    rån
    0.47
     كومونز
    0.47
     colo
    0.44
    Atsauces
    0.43
     Mait
    0.42
    Bronnen
    0.42
    Activations Density 0.721%

    No Known Activations