© 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. 33-GEMMASCOPE-RES-16K
    11. 14105
    Prev
    Next
    INDEX
    Explanations

    questions directed at the reader or listener, often starting with "Do you" or involving the word "you"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.77
     مشين
    -0.72
     is
    -0.69
     will
    -0.68
     might
    -0.67
    ConstraintMaker
    -0.63
    PostExecute
    -0.63
     would
    -0.63
     should
    -0.61
     was
    -0.60
    POSITIVE LOGITS
     ever
    0.57
     not
    0.55
     acaso
    0.50
     Autorizaciones
    0.43
     supposed
    0.42
     jemals
    0.40
     possibly
    0.39
     going
    0.39
     EVER
    0.37
     siis
    0.37
    Activations Density 0.244%

    No Known Activations