Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3977
    Prev
    Next
    INDEX
    Explanations

    declarations and definitions related to data types and structures in programming

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

    Code containing the word "String"

    np_acts-logits-general · gemini-2.0-flash

    types like string within code constructs

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    __*/
    -0.74
     ""],
    -0.73
    InitVars
    -0.65
     *)__
    -0.55
    Према
    -0.54
    >';
    
    -0.53
    ///</
    -0.52
    ền
    -0.52
     <",
    -0.51
    apor
    -0.50
    POSITIVE LOGITS
    IntoConstraints
    0.77
    ंदीखरीदारी
    0.68
    RectangleBorder
    0.64
     MainAxisSize
    0.63
     يتيمه
    0.61
    reportWebVitals
    0.60
     تانيه
    0.57
    ChildScrollView
    0.57
    ExecuteReader
    0.57
    middels
    0.56
    Activations Density 0.085%

    No Known Activations