© 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. 14796
    Prev
    Next
    INDEX
    Explanations

    JavaScript script tags and their attributes

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

    Code within HTML script tags

    np_acts-logits-general · gemini-2.0-flash

    script src attributes

    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
    ⓘ
    -0.79
    MockBean
    -0.69
     يتيمه
    -0.62
     EClass
    -0.62
    __*/
    -0.62
    AnchorTagHelper
    -0.60
     trebui
    -0.56
    IntoConstraints
    -0.56
    sizeCache
    -0.55
     ModelExpression
    -0.54
    POSITIVE LOGITS
     src
    0.93
    src
    0.74
     language
    0.71
     defer
    0.67
     LANGUAGE
    0.64
    language
    0.62
    SRC
    0.60
    Language
    0.60
     Language
    0.59
    Src
    0.59
    Activations Density 0.105%

    No Known Activations