© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 15147
    Prev
    Next
    INDEX
    Explanations

    educational content related to teaching concepts and basic problem-solving methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Бахар
    -0.53
     jouets
    -0.53
     poussière
    -0.52
     détru
    -0.52
     pregunto
    -0.51
    atguigu
    -0.51
    ("]");
    -0.51
     exhibición
    -0.50
     partenza
    -0.49
     larmes
    -0.49
    POSITIVE LOGITS
     fractions
    0.89
     decimals
    0.80
     Fractions
    0.79
     quadratic
    0.77
     probability
    0.73
     percentages
    0.73
     trigon
    0.73
     Fibonacci
    0.70
    probability
    0.69
     vectors
    0.68
    Activations Density 1.442%

    No Known Activations