© 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. 33-GEMMASCOPE-RES-16K
    11. 13658
    Prev
    Next
    INDEX
    Explanations

    URLs and related web paths, particularly those from Google and Microsoft

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    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
    -0.61
     للمعارف
    -0.58
    enderror
    -0.54
    EndContext
    -0.54
    initComponents
    -0.54
    queryInterface
    -0.53
     typelib
    -0.53
    RTDA
    -0.51
    UnusedPrivate
    -0.49
    webElementXpaths
    -0.47
    POSITIVE LOGITS
     en
    1.00
    en
    0.74
     EN
    0.70
    EN
    0.68
     fr
    0.58
    fr
    0.54
     zh
    0.52
    enus
    0.50
     nl
    0.49
     FR
    0.47
    Activations Density 0.467%

    No Known Activations