© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 4785
    Prev
    Next
    INDEX
    Explanations

    comparative phrases that use the word "as."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 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
    endphp
    -0.73
    ագրություններ
    -0.69
    InitVars
    -0.67
     مشين
    -0.65
    مراجع
    -0.65
    ETIME
    -0.63
    تفصیلات
    -0.63
    λίου
    -0.62
    DebuggerStep
    -0.61
    -------
    -0.61
    POSITIVE LOGITS
     πως
    0.57
    tifying
    0.56
     oorsp
    0.52
    Legături
    0.51
     oprot
    0.50
     Abstand
    0.50
    Dion
    0.49
    anskje
    0.48
     obicei
    0.47
     Dion
    0.47
    Activations Density 0.356%

    No Known Activations