© 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. 1-GEMMASCOPE-RES-16K
    11. 4870
    Prev
    Next
    INDEX
    Explanations

    percentage symbols and numerical values related to percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ấu
    -0.45
     Eisen
    -0.40
    хьтан
    -0.38
     READ
    -0.37
    underline
    -0.36
    READ
    -0.36
     Schu
    -0.35
    RTLR
    -0.35
     Sand
    -0.35
    include
    -0.34
    POSITIVE LOGITS
     %
    2.81
    %
    2.64
     \%
    2.59
     $\%$
    2.45
     $\%
    2.44
    \%
    2.34
     (%
    2.34
     \%$
    2.28
     '%
    2.27
    $\%$
    2.27
    Activations Density 0.303%

    No Known Activations