© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 24-GEMMASCOPE-RES-16K
    6. 7042
    Prev
    Next
    INDEX
    Explanations

    instances of code syntax and function definitions

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

    The token "var"

    np_acts-logits-general · gemini-2.0-flash

    variable declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     `${
    -0.69
     eslint
    -0.67
    >{@
    -0.66
    ']))
    
    -0.65
    WebVitals
    -0.63
    ():
    
    -0.62
    `${
    -0.61
    ]));
    
    -0.59
     disambiguazione
    -0.58
    <>
    
    -0.57
    POSITIVE LOGITS
    var
    3.44
     var
    3.01
    Var
    1.82
    VAR
    1.80
     Var
    1.74
     VAR
    1.56
    vara
    1.42
     vari
    1.41
     variable
    1.34
    vari
    1.28
    Activations Density 0.108%

    No Known Activations