© 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. 13259
    Prev
    Next
    INDEX
    Explanations

    syntax elements related to object and function definitions in programming languages

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

    Code or list-like structures

    np_acts-logits-general · gemini-2.0-flash

    <code>` or `" ` followed by text

    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
    MessageTagHelper
    -0.58
     <=",
    -0.57
     ModelExpression
    -0.56
     [](
    -0.55
     ")");
    -0.55
     صوتيه
    -0.54
     [],
    -0.52
    ⋱
    -0.50
     {}),
    -0.50
     []);
    -0.49
    POSITIVE LOGITS
     '
    1.09
     ‘
    0.89
    ('
    0.77
     "
    0.76
     ’
    0.74
    ‘
    0.72
    nameof
    0.72
    endphp
    0.69
     ‚
    0.68
     MainAxisSize
    0.66
    Activations Density 0.182%

    No Known Activations