© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10554
    Prev
    Next
    INDEX
    Explanations

    sentences that discuss characters' relationships and personal development

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     aporta
    -0.37
     oído
    -0.35
     jaula
    -0.34
     contribution
    -0.34
     rodilla
    -0.33
     explanation
    -0.33
    WriteLiteral
    -0.32
     contribuye
    -0.32
     mediodía
    -0.31
     campamento
    -0.31
    POSITIVE LOGITS
    ########.
    0.63
     StatefulWidget
    0.60
    MigrationBuilder
    0.60
    CGRectMake
    0.59
    主人公
    0.59
    featureID
    0.58
     protagonist
    0.58
    verwijspagina
    0.58
    oneofs
    0.57
    StackNavigator
    0.57
    Activations Density 0.450%

    No Known Activations