© 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. 27-GEMMASCOPE-RES-16K
    11. 11795
    Prev
    Next
    INDEX
    Explanations

    structured elements and references in academic and legal texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/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.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.48
     HasFactory
    -0.48
     oprot
    -0.46
    IsContent
    -0.46
    rrggbb
    -0.45
     transfieras
    -0.43
    DebuggerNonUser
    -0.39
    RectangleBorder
    -0.38
    solete
    -0.38
     endforeach
    -0.37
    POSITIVE LOGITS
    EndGlobalSection
    0.57
    Hentet
    0.53
    хьтан
    0.50
    Diwedd
    0.48
     resourceCulture
    0.47
    MENAFN
    0.43
     дописавши
    0.43
     Meksiku
    0.43
     للاسماء
    0.42
    ithub
    0.42
    Activations Density 0.787%

    No Known Activations