© 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. 4-GEMMASCOPE-RES-16K
    6. 3623
    Prev
    Next
    INDEX
    Explanations

    syntactical elements related to data structures in programming, primarily in the context of maps and lists

    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
     libera
    -0.47
    parently
    -0.47
    observations
    -0.44
    ศาสตร์
    -0.43
     bekijken
    -0.42
    malıdır
    -0.42
    ayuda
    -0.42
     terakhir
    -0.42
    unfortunately
    -0.42
     gén
    -0.42
    POSITIVE LOGITS
    ValueGeneration
    0.91
    addCriterion
    0.88
     Meksiku
    0.77
     BoxFit
    0.73
    ={[
    0.72
    QMetaType
    0.70
    Personendaten
    0.70
     Margot
    0.70
     ExecuteAsync
    0.69
    dymyr
    0.69
    Activations Density 0.170%

    No Known Activations