© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 6373
    Prev
    Next
    INDEX
    Explanations

    formal definitions and scientific terminology related to functions and structures

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

    C preprocessor definitions starting with "F_"

    np_acts-logits-general · gemini-2.0-flash

    `F` followed by underscore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.64
    expandindo
    -0.62
    httphttps
    -0.60
    ThemeOverlay
    -0.56
    ötzlich
    -0.56
     queſta
    -0.54
     Diar
    -0.53
    Nicky
    -0.53
    cheinend
    -0.52
     OnDestroy
    -0.52
    POSITIVE LOGITS
     f
    0.87
    F
    0.86
     F
    0.81
    f
    0.75
     getF
    0.69
     फ
    0.67
    FE
    0.66
    ฟ
    0.66
    fe
    0.60
     Ф
    0.59
    Activations Density 3.045%

    No Known Activations