© 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. 14-GEMMASCOPE-RES-16K
    11. 12003
    Prev
    Next
    INDEX
    Explanations

    statements relating to future actions or predictions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ViewFeatures
    -0.47
    transQ
    -0.43
    runOnUiThread
    -0.43
    Trama
    -0.43
    atshirt
    -0.42
    Morfologia
    -0.40
     baritone
    -0.40
     sord
    -0.40
     cod
    -0.40
    География
    -0.39
    POSITIVE LOGITS
     will
    0.96
    will
    0.81
     zullen
    0.76
     zult
    0.73
     będzie
    0.71
     Will
    0.69
    Will
    0.67
     saranno
    0.67
     youll
    0.63
     bude
    0.62
    Activations Density 1.062%

    No Known Activations