© 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. 34-GEMMASCOPE-RES-16K
    11. 9432
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries about solutions or alternatives in a discussion or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -0.78
     للاسماء
    -0.63
    SharedDtor
    -0.63
    новништво
    -0.59
    AndEndTag
    -0.57
    UseVisualStyle
    -0.55
    AddTagHelper
    -0.53
    mergeFrom
    -0.53
    ConstraintMaker
    -0.53
    Життєпис
    -0.50
    POSITIVE LOGITS
     there
    3.88
    there
    2.78
    There
    2.58
     There
    2.52
     THERE
    2.31
     هناك
    2.06
    THERE
    1.97
     theres
    1.63
     есть
    1.47
    theres
    1.45
    Activations Density 2.555%

    No Known Activations