© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 1582
    Prev
    Next
    INDEX
    Explanations

    structural components and features in descriptions of physical objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     réf
    -0.32
    localctx
    -0.32
     sworn
    -0.29
    UrlResolution
    -0.29
     rápida
    -0.29
     meridional
    -0.28
     muñecas
    -0.28
    delimiter
    -0.28
    cionada
    -0.28
     снять
    -0.28
    POSITIVE LOGITS
     protruding
    1.43
     protr
    1.37
     projecting
    1.16
     exposed
    1.08
    exposed
    1.05
     poking
    1.01
     Exposed
    1.00
     overhang
    0.98
     jut
    0.97
    Exposed
    0.94
    Activations Density 0.719%

    No Known Activations