© 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. 8439
    Prev
    Next
    INDEX
    Explanations

    elements related to formatting and structure in code or data

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

    Newline characters

    np_acts-logits-general · gemini-2.0-flash

    carriage return and newline

    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
    __((
    -0.61
     AssemblyProduct
    -0.60
     numerus
    -0.56
     ComVisible
    -0.52
     Paglinawan
    -0.50
     <=",
    -0.50
     auprès
    -0.49
     تانيه
    -0.48
     contextLoads
    -0.48
    ThroughAttribute
    -0.48
    POSITIVE LOGITS
     newline
    1.00
    NewLine
    0.83
    newline
    0.79
    newLine
    0.75
    ,"\
    0.69
     "\
    0.68
     line
    0.68
    ="\
    0.64
     LINE
    0.64
    nextLine
    0.64
    Activations Density 0.417%

    No Known Activations