© 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. 31-GEMMASCOPE-RES-16K
    11. 5060
    Prev
    Next
    INDEX
    Explanations

    quantitative data and statistical measures related to structures or groups

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

    numerical ranges and comparisons involving inequality operators or threshold values.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    smaller
    -0.66
     mindre
    -0.65
     Smaller
    -0.63
    Smaller
    -0.62
     smaller
    -0.60
    Low
    -0.57
     düşük
    -0.57
     Fewer
    -0.56
     fewer
    -0.56
     low
    -0.56
    POSITIVE LOGITS
     ≥
    1.02
    ≥
    1.02
     >=
    1.01
     greater
    0.99
     above
    0.96
     >
    0.95
     $>
    0.85
    大于
    0.84
    >=
    0.84
    greater
    0.82
    Activations Density 0.878%

    No Known Activations