© 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. 7497
    Prev
    Next
    INDEX
    Explanations

    identifiers and variable names in code snippets

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

    Code snippets with brackets/parentheses

    np_acts-logits-general · gemini-2.0-flash

    closing bracket ) } ]

    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
     Sche
    -0.47
    亿美元
    -0.45
    ImageField
    -0.45
    messe
    -0.44
     miễn
    -0.44
     Prevent
    -0.42
     tra
    -0.41
     med
    -0.41
     Bear
    -0.40
    சு
    -0.40
    POSITIVE LOGITS
     snippetHide
    0.74
     Efq
    0.72
     AssemblyCulture
    0.72
    RegressionTest
    0.70
    )->
    0.68
    ")->
    0.67
     Lordships
    0.67
    ]->
    0.66
    //});
    0.65
     Мексичка
    0.65
    Activations Density 0.399%

    No Known Activations