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. 3318
    Prev
    Next
    INDEX
    Explanations

    elements related to abstract syntax tree (AST) nodes and their properties in programming

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

    Code elements related to syntax, identifiers, and AST nodes

    np_acts-logits-general · gemini-2.0-flash

    node name or identifier

    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
     esternos
    -0.54
    OGND
    -0.47
    AutoresizingMask
    -0.45
    phosa
    -0.42
    EditorBrowsable
    -0.42
     Obrador
    -0.41
    bootstrapcdn
    -0.41
    Paying
    -0.40
     FormsModule
    -0.40
    MockBean
    -0.39
    POSITIVE LOGITS
    から
    0.67
    ify
    0.64
     से
    0.64
    "](
    0.63
    TimeTo
    0.62
    dify
    0.61
    
    0.60
    StringTo
    0.60
     Архів
    0.60
    Abitanti
    0.58
    Activations Density 0.421%

    No Known Activations