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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 1056
    Prev
    Next
    INDEX
    Explanations

    function definitions and calls in code

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

    the presence of method definitions in code

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

    automatically

    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
     بيها
    -0.73
    Hentet
    -0.67
    neté
    -0.67
     AssemblyCulture
    -0.67
    MLLoader
    -0.66
     EClass
    -0.66
    XmlType
    -0.64
    звание
    -0.62
    UnknownFields
    -0.62
     мәкалә
    -0.62
    POSITIVE LOGITS
    ])):
    1.00
    ():
    0.85
    ):
    0.84
    >):
    0.83
    ↵
    0.73
    ()):
    0.72
    '):
    0.71
    ]):
    0.69
    "):
    0.65
     ():
    0.64
    Activations Density 0.005%

    No Known Activations