© 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. 23-GEMMASCOPE-RES-16K
    11. 3488
    Prev
    Next
    INDEX
    Explanations

    technical terms and metrics related to scientific and statistical data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/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.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.43
     persil
    -0.43
    épar
    -0.42
    DebuggerStep
    -0.42
    adaptiveStyles
    -0.42
     Krakowie
    -0.41
     capables
    -0.41
     Arabidopsis
    -0.41
    lujah
    -0.41
     éc
    -0.41
    POSITIVE LOGITS
     both
    0.58
    点此举报
    0.53
     onCreateView
    0.52
    存于互联网档案馆
    0.50
     components
    0.47
     BOTH
    0.46
    Hozzáférés
    0.46
    components
    0.45
     Both
    0.45
    Xna
    0.45
    Activations Density 1.293%

    No Known Activations