© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2950
    Prev
    Next
    INDEX
    Explanations

    terms related to web development, particularly those involving user interactions and UI components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    terms related to technical and programming contexts, particularly around API usage and data handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets or related technical instructions

    np_acts-logits-general · gemini-2.0-flash

    program execution flow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     garcía
    -0.65
     graças
    -0.57
     sérieux
    -0.57
     battre
    -0.56
     trouva
    -0.54
     sogni
    -0.53
     Jérusalem
    -0.53
     delantera
    -0.52
     savent
    -0.52
     honnête
    -0.52
    POSITIVE LOGITS
     upto
    0.80
     irrespective
    0.78
     hence
    0.77
     Hence
    0.76
    Hence
    0.75
    upto
    0.75
     atleast
    0.74
    noOf
    0.68
    respective
    0.67
     alphabets
    0.67
    Activations Density 0.742%

    No Known Activations