Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12960
    Prev
    Next
    INDEX
    Explanations

    symbols and mathematical notation used in equations and proofs

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

    Mathematical or specialized notation

    np_acts-logits-general · gemini-2.0-flash

    LaTeX mathematics, symbols, and spacing

    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
     utafitiHapana
    -0.54
    VersionUID
    -0.53
     يتيمه
    -0.53
     Koto
    -0.52
    ."+
    -0.48
    znik
    -0.48
    CAPIT
    -0.48
    +".
    -0.47
    $)$
    -0.47
     oprot
    -0.46
    POSITIVE LOGITS
    quad
    0.68
    forall
    0.67
    ∀
    0.64
     personnalisés
    0.60
     financière
    0.58
     solange
    0.58
     financeira
    0.58
     malattia
    0.58
    PrototypeOf
    0.57
    المشاركات
    0.57
    Activations Density 0.883%

    No Known Activations