© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 2711
    Prev
    Next
    INDEX
    Explanations

    characters and symbols in the document, particularly those associated with mathematical expressions or 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
     ervoor
    -0.53
     tačiau
    -0.53
    bigsqcup
    -0.49
    agaimana
    -0.48
    ographical
    -0.47
    zonego
    -0.47
    anding
    -0.47
     vastaan
    -0.46
     īpa
    -0.46
     kautta
    -0.45
    POSITIVE LOGITS
    GEBURTSDATUM
    0.92
     estekak
    0.73
    UnusedPrivate
    0.70
    IUrlHelper
    0.69
    RenderAtEndOf
    0.67
    adaptiveStyles
    0.64
    tagHelperRunner
    0.63
     disambiguazione
    0.61
    webElementGuid
    0.61
    RegressionTest
    0.60
    Activations Density 2.926%

    No Known Activations