© 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. 35-GEMMASCOPE-RES-16K
    11. 4681
    Prev
    Next
    INDEX
    Explanations

    instances of the word "two" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ly
    -0.54
     Grüsse
    -0.45
     habitudes
    -0.44
     variés
    -0.44
     centaines
    -0.42
     négociations
    -0.42
     pelbagai
    -0.42
    igón
    -0.42
     répar
    -0.41
     mesto
    -0.40
    POSITIVE LOGITS
     halves
    0.77
     extremes
    0.71
    thirds
    0.71
     thirds
    0.71
     hemispheres
    0.68
     sides
    0.63
     separate
    0.60
     contrasting
    0.59
     distinct
    0.58
     opposing
    0.56
    Activations Density 0.290%

    No Known Activations