© 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. 40-GEMMASCOPE-RES-16K
    11. 7404
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and concepts related to matrix and statistical properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tématu
    -0.41
     Meksiku
    -0.36
    ysacchar
    -0.35
    MessageTagHelper
    -0.34
     étages
    -0.33
     Signalez
    -0.33
    ądze
    -0.33
     fortalec
    -0.32
    頰
    -0.31
    JspWriter
    -0.31
    POSITIVE LOGITS
     zero
    3.78
     Zero
    3.31
    zero
    3.22
    Zero
    3.09
     ZERO
    3.03
    ZERO
    2.70
     zéro
    2.69
     cero
    2.67
    ゼロ
    2.48
     zeros
    2.47
    Activations Density 1.404%

    No Known Activations