© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 937
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation marks used in programming and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.56
     (
    -0.52
     [
    -0.48
     rowspan
    -0.46
     No
    -0.46
    </blockquote>
    -0.45
    ┓
    -0.45
    ↵↵↵
    -0.44
    baarheid
    -0.42
     His
    -0.42
    POSITIVE LOGITS
    onViewCreated
    0.92
    ✨:
    0.86
    contentLoaded
    0.72
     validamos
    0.72
     moor
    0.69
    ⓘ
    0.67
    جمعیت
    0.65
     stället
    0.65
     Dispens
    0.64
    Skocz
    0.64
    Activations Density 1.042%

    No Known Activations