© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 1975
    Prev
    Next
    INDEX
    Explanations

    syntactical elements and code structure in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dieťa
    -0.56
     rispet
    -0.52
    бенок
    -0.52
     communis
    -0.51
    ďaka
    -0.50
     Auvergne
    -0.48
     Timoteo
    -0.47
    ffine
    -0.47
    iség
    -0.46
     poświę
    -0.46
    POSITIVE LOGITS
    OGND
    0.92
    WebVitals
    0.85
    SourceChecksum
    0.82
    +#+#
    0.82
    LookAnd
    0.82
    UnknownFieldSet
    0.79
     '{@
    0.78
     resourceCulture
    0.78
    esez
    0.73
    !("{}",
    0.71
    Activations Density 0.081%

    No Known Activations