© 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. 1-GEMMASCOPE-RES-16K
    6. 4960
    Prev
    Next
    INDEX
    Explanations

    occurrences of mathematical notation and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Majefty
    -0.95
     itſelf
    -0.92
    adaptiveStyles
    -0.91
    NOPQRST
    -0.90
     themſelves
    -0.89
     विश्वसनीयता
    -0.86
    webElementXpaths
    -0.85
     poffe
    -0.85
     Jefus
    -0.84
     himſelf
    -0.83
    POSITIVE LOGITS
    }>{
    0.66
    <sup>
    0.64
    [toxicity=0]
    0.58
    '>{
    0.57
    <b>
    0.56
    <i>
    0.56
    ${
    0.54
    <sub>
    0.52
    </
    0.52
    {{\
    0.52
    Activations Density 0.213%

    No Known Activations