© 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. 18-GEMMASCOPE-RES-16K
    11. 887
    Prev
    Next
    INDEX
    Explanations

    code structure and syntax patterns in programming language documents

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

    Opening parenthesis followed by data types, especially "String"

    np_acts-logits-general · gemini-2.0-flash

    function signatures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     int
    -0.83
     numbers
    -0.82
     Numbers
    -0.82
     integer
    -0.81
    Integer
    -0.79
     parseInt
    -0.76
    Numbers
    -0.76
    SetInt
    -0.75
    int
    -0.75
     Integer
    -0.75
    POSITIVE LOGITS
    String
    0.65
     String
    0.63
    BeginContext
    0.63
    DebuggerNonUser
    0.60
    matchCondition
    0.59
    exitRule
    0.58
    WebElementEntity
    0.57
    WebServlet
    0.54
    STRING
    0.54
     string
    0.54
    Activations Density 0.092%

    No Known Activations