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. 22-GEMMASCOPE-RES-16K
    6. 10278
    Prev
    Next
    INDEX
    Explanations

    terms related to programming syntax and variable naming conventions

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

    Punctuation and spacing after tokens

    np_acts-logits-general · gemini-2.0-flash

    whitespace and punctuation

    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
    localctx
    -0.79
     المعيارى
    -0.75
    )");
    
    -0.74
    ")));
    
    -0.72
    ')")
    -0.72
     ""))
    -0.69
     }}"></
    -0.69
    >");
    
    -0.69
    ']")
    -0.68
    IVEREF
    -0.66
    POSITIVE LOGITS
     spaces
    1.14
     space
    1.08
     dashes
    1.03
     dot
    0.98
    spaces
    0.96
     dash
    0.95
     Spaces
    0.94
     slash
    0.93
    space
    0.93
     underscore
    0.92
    Activations Density 0.908%

    No Known Activations