© 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. 4045
    Prev
    Next
    INDEX
    Explanations

    questions that inquire about reasons or justifications

    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
    UCC
    -0.57
    providedIn
    -0.57
     GSC
    -0.55
    uVar
    -0.51
     Golem
    -0.50
    GCC
    -0.50
    UnitTesting
    -0.48
    NCS
    -0.48
    oulli
    -0.48
     getResult
    -0.48
    POSITIVE LOGITS
     why
    1.14
    Why
    1.09
     Why
    1.09
    why
    1.09
     WHY
    1.01
    WHY
    0.99
     Whyte
    0.98
     Pourquoi
    0.94
    Pourquoi
    0.93
     Waarom
    0.92
    Activations Density 0.077%

    No Known Activations