© 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. 22-GEMMASCOPE-RES-16K
    11. 5745
    Prev
    Next
    INDEX
    Explanations

    items related to code structure and library inclusion in programming languages

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

    Includes within C++ files

    np_acts-logits-general · gemini-2.0-flash

    C++ header includes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     siap
    -0.46
    marshaller
    -0.46
     έκ
    -0.46
    ppelt
    -0.45
    AttributeSet
    -0.44
    xtext
    -0.43
     dispuesto
    -0.43
    ContentAlignment
    -0.43
     kautta
    -0.43
     MacKenzie
    -0.42
    POSITIVE LOGITS
     Савезне
    0.79
     myſelf
    0.78
    expandindo
    0.75
     AssemblyCulture
    0.73
     $_"
    0.73
     للاسماء
    0.71
    limits
    0.71
    tagHelperRunner
    0.71
     MainAxisSize
    0.69
    assert
    0.69
    Activations Density 0.121%

    No Known Activations