© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 573
    Prev
    Next
    INDEX
    Explanations

    key phrases related to programming and coding concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    terms related to managing and clearing debt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    basic concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    migrationBuilder
    -0.75
    WithIOException
    -0.74
    SourceChecksum
    -0.73
    rungsseite
    -0.72
    ValueStyle
    -0.64
    BufferException
    -0.63
     متعلقه
    -0.63
    rsiniz
    -0.61
     AssemblyProduct
    -0.59
    windowFixed
    -0.59
    POSITIVE LOGITS
     basic
    2.41
    basic
    2.14
     simple
    2.09
    Basic
    2.00
     simplest
    1.97
     Basic
    1.94
     basics
    1.84
    simple
    1.79
     básico
    1.78
     básicas
    1.70
    Activations Density 0.352%

    No Known Activations