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. 8111
    Prev
    Next
    INDEX
    Explanations

    programming constructs and syntax related to functions and variables

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

    Code indentation and spacing

    np_acts-logits-general · gemini-2.0-flash

    indentation and spacing

    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
     exist
    -0.51
     HttpNotFound
    -0.51
    省市镇
    -0.50
    PRNewswire
    -0.50
    jspx
    -0.49
    imread
    -0.48
    UnsafeEnabled
    -0.47
     المعيارى
    -0.47
    liar
    -0.46
    ğraf
    -0.46
    POSITIVE LOGITS
    IndentedString
    0.75
     indentation
    0.68
     indent
    0.68
    Spaces
    0.67
     tabs
    0.67
     TAB
    0.66
     spaces
    0.66
    GEBURTSDATUM
    0.65
    spaces
    0.62
     tab
    0.62
    Activations Density 0.306%

    No Known Activations