© 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. 27-GEMMASCOPE-RES-16K
    11. 11673
    Prev
    Next
    INDEX
    Explanations

    connections between historical records and the evolution of ideas or practices over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sede
    -0.34
     chapéu
    -0.30
     ujedno
    -0.30
    getSingle
    -0.29
     समीक्षाएं
    -0.28
    leich
    -0.28
     strijd
    -0.28
     neón
    -0.27
    Biographie
    -0.26
    olverine
    -0.26
    POSITIVE LOGITS
     jusqu
    1.52
     hasta
    1.48
     until
    1.42
     till
    1.34
     jusque
    1.32
     até
    1.31
    until
    1.25
     sampai
    1.23
    jusqu
    1.23
    hasta
    1.22
    Activations Density 0.564%

    No Known Activations