© 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. 22-GEMMASCOPE-RES-16K
    11. 13398
    Prev
    Next
    INDEX
    Explanations

    terms related to global and national scales

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poca
    -0.31
    الط
    -0.30
    留在
    -0.28
    ThroughAttribute
    -0.28
     chapter
    -0.28
    POP
    -0.27
    glTex
    -0.27
     arka
    -0.27
     компо
    -0.27
     or
    -0.27
    POSITIVE LOGITS
    Worldwide
    0.75
     worldwide
    0.71
     MainAxisSize
    0.69
    worldwide
    0.68
     Worldwide
    0.66
    AddHtmlAttribute
    0.65
     nationwide
    0.63
    copg
    0.62
     světě
    0.61
    AndroidJUnit
    0.60
    Activations Density 0.366%

    No Known Activations