© 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. 12122
    Prev
    Next
    INDEX
    Explanations

    enumerations and structural elements in formal documents

    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
     meta
    -0.50
     Systematic
    -0.48
     systematic
    -0.47
     perſon
    -0.47
    meta
    -0.46
    Према
    -0.46
     Meta
    -0.45
     ſmall
    -0.42
    Systematic
    -0.41
    sys
    -0.41
    POSITIVE LOGITS
     VII
    1.06
     VIII
    1.02
     III
    0.99
     iii
    0.97
    VII
    0.94
    iii
    0.94
     vii
    0.93
    III
    0.93
    VIII
    0.92
     IV
    0.91
    Activations Density 0.361%

    No Known Activations