© 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. 10-GEMMASCOPE-RES-16K
    6. 16218
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and properties related to functions and their bounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.86
    jooq
    -0.68
    OrBuilder
    -0.65
    RuleContext
    -0.63
    WriteBarrier
    -0.63
    migrationBuilder
    -0.62
    Искәрмәләр
    -0.61
     ExecuteAsync
    -0.60
    intracht
    -0.60
    */].
    -0.59
    POSITIVE LOGITS
    hånd
    0.52
     AssemblyVersion
    0.48
    TimePicker
    0.47
    Mitglieder
    0.47
    InSection
    0.46
     besky
    0.45
    ordning
    0.45
     torneo
    0.44
     Alive
    0.44
     pove
    0.43
    Activations Density 1.678%

    No Known Activations