© 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. 11-GEMMASCOPE-RES-16K
    11. 11489
    Prev
    Next
    INDEX
    Explanations

    statistical data and confidence intervals related to study results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zase
    -0.24
     utafitiHapana
    -0.23
     permanently
    -0.23
     criança
    -0.23
     Absch
    -0.22
    有名
    -0.22
     hook
    -0.22
     tradicional
    -0.22
    ************/
    -0.21
     Zap
    -0.21
    POSITIVE LOGITS
    ContentAsync
    0.87
    yarnpkg
    0.74
     Normdatei
    0.73
    JspWriter
    0.73
     CreateTagHelper
    0.72
     препратки
    0.70
    RectangleBorder
    0.69
    <unused52>
    0.68
    ThroughAttribute
    0.68
    [@BOS@]
    0.67
    Activations Density 2.805%

    No Known Activations