© 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. 22-GEMMASCOPE-RES-16K
    6. 15402
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving fractions and derivatives

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

    Mathematical notation/equations

    np_acts-logits-general · gemini-2.0-flash

    mathematical derivatives and sums

    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
    ----</
    -0.64
    {}'.
    -0.61
     etc
    -0.60
    󠁴
    -0.56
    /');
    -0.55
    igslist
    -0.53
    ांकि
    -0.53
     estimés
    -0.53
    Màu
    -0.52
    çade
    -0.52
    POSITIVE LOGITS
    IMPORTED
    0.75
     }{
    0.68
     insensible
    0.65
     الاطلاع
    0.65
    *}{
    0.64
    partial
    0.63
    TagMode
    0.63
    Datuak
    0.62
     وصلة
    0.62
     umane
    0.60
    Activations Density 0.220%

    No Known Activations