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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 2764
    Prev
    Next
    INDEX
    Explanations

    programming constructs and their structural elements within code

    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
    日閲覧
    -0.69
    gebnisse
    -0.62
     pinulongan
    -0.62
    Parabéns
    -0.59
     صوتيه
    -0.56
    kmale
    -0.52
    DoubleQuotes
    -0.51
    hysema
    -0.51
     jScrollPane
    -0.51
     ExecuteAsync
    -0.50
    POSITIVE LOGITS
    func
    0.99
     func
    0.85
    override
    0.77
    init
    0.67
    fileprivate
    0.66
    deinit
    0.65
    convenience
    0.65
    lazy
    0.62
    @
    0.62
    var
    0.62
    Activations Density 0.187%

    No Known Activations