© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 4745
    Prev
    Next
    INDEX
    Explanations

    programming syntax and code elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ROW
    -0.57
     row
    -0.56
     rows
    -0.55
     Económica
    -0.53
     titulaire
    -0.53
     Monfieur
    -0.53
    row
    -0.52
     Row
    -0.52
     mauve
    -0.52
     Deng
    -0.51
    POSITIVE LOGITS
    Tikang
    0.72
    //</
    0.64
    횟
    0.59
    GraphicsUnit
    0.55
    /");
    0.54
     *);
    0.53
     gynnwys
    0.53
    __);
    0.53
    */),
    0.53
    )}</
    0.51
    Activations Density 0.059%

    No Known Activations