© 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 - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 9359
    Prev
    Next
    INDEX
    Explanations

    keywords related to boolean logic and data types

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

    boolean variables and operators

    np_acts-logits-general · gemini-2.0-flash

    boolean types and declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Spence
    -0.54
    ive
    -0.53
    ρους
    -0.53
    де
    -0.53
     Schmid
    -0.53
    ợi
    -0.53
     مد
    -0.52
    IVES
    -0.52
     Pio
    -0.51
    ので
    -0.50
    POSITIVE LOGITS
    MigrationBuilder
    1.13
    stdbool
    1.09
    MethodManager
    1.08
     Bool
    0.96
    ArgsConstructor
    0.94
    getBoolean
    0.92
    oolean
    0.91
    BooleanField
    0.88
     disponibilités
    0.86
     bool
    0.85
    Activations Density 0.042%

    No Known Activations