© 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. 1632
    Prev
    Next
    INDEX
    Explanations

    code related to SQL queries and connection management in programming contexts

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

    Code, queries, or commands

    np_acts-logits-general · gemini-2.0-flash

    expressions and statements

    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
    andaag
    -0.56
     vertus
    -0.56
     preocu
    -0.50
     invokingState
    -0.50
    AutoField
    -0.49
     goû
    -0.48
    petto
    -0.47
    }{|
    -0.47
     Процитовано
    -0.47
     estimé
    -0.47
    POSITIVE LOGITS
     expression
    1.07
     statement
    1.00
     expressions
    0.93
    expression
    0.90
     formula
    0.87
     statements
    0.86
     sentence
    0.81
    statement
    0.79
     Statement
    0.79
     Expression
    0.78
    Activations Density 0.777%

    No Known Activations