© 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. 15-GEMMASCOPE-RES-16K
    11. 5928
    Prev
    Next
    INDEX
    Explanations

    references to principles or key concepts in a theoretical or methodological context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.60
     Hobson
    -0.54
    onews
    -0.52
     setTotal
    -0.51
    Tob
    -0.50
    defe
    -0.50
    Hob
    -0.50
    SourceChecksum
    -0.48
     Tod
    -0.48
     Estat
    -0.48
    POSITIVE LOGITS
     Prin
    0.58
    prin
    0.55
     Spring
    0.55
    Principle
    0.54
    Prin
    0.52
     Springs
    0.52
    Spring
    0.51
     Principle
    0.48
    prit
    0.48
     Springer
    0.48
    Activations Density 0.198%

    No Known Activations