© 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. 37-GEMMASCOPE-RES-16K
    11. 8230
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CodedInputStream
    -0.42
    󠁴
    -0.42
     становника
    -0.40
     metav
    -0.37
    HideFlags
    -0.37
    jsxFileName
    -0.37
     Meksiku
    -0.37
     geïsole
    -0.36
    BASELINE
    -0.36
    InjectAttribute
    -0.35
    POSITIVE LOGITS
    tschaft
    0.59
    begin
    0.58
    subsection
    0.54
    section
    0.51
     begin
    0.50
    '));
    0.48
    出版年
    0.48
     iconLine
    0.47
    subsubsection
    0.47
    setcounter
    0.47
    Activations Density 0.352%

    No Known Activations