© 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. 30-GEMMASCOPE-RES-16K
    11. 14486
    Prev
    Next
    INDEX
    Explanations

    numerical values related to frame rates in video or graphics contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Numbers between 0 and 9

    np_acts-logits-general · gemini-2.0-flash

    percentages and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.65
    tonsoft
    -0.64
     transfieras
    -0.64
     Roskov
    -0.63
     EconPapers
    -0.62
    ActionCreators
    -0.57
    httphttps
    -0.56
     resourceCulture
    -0.56
    webElementXpaths
    -0.56
    estacks
    -0.55
    POSITIVE LOGITS
    %
    0.51
     percent
    0.44
    percent
    0.43
    %+
    0.43
     Prozent
    0.40
    \%
    0.40
    %-
    0.39
    ers
    0.39
     kDa
    0.39
    %.
    0.36
    Activations Density 1.589%

    No Known Activations