© 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. 41-GEMMASCOPE-RES-16K
    11. 5066
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to understanding problems and seeking knowledge

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.63
    addCriterion
    -0.51
    хьтан
    -0.47
     урна
    -0.44
    RenderAtEndOf
    -0.44
    IntoConstraints
    -0.43
     ModelExpression
    -0.42
    Tracce
    -0.40
    LookAnd
    -0.40
    UseVisualStyle
    -0.40
    POSITIVE LOGITS
     how
    3.88
     cómo
    2.25
     bagaimana
    2.09
    how
    2.03
     hvordan
    1.92
    如何
    1.69
     nasıl
    1.63
    How
    1.63
     كيف
    1.59
     miten
    1.57
    Activations Density 0.952%

    No Known Activations