© 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. 25-GEMMASCOPE-RES-16K
    11. 32
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and notation, particularly related to theorems and proofs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TintMode
    -0.70
    InputBorder
    -0.67
    GOTREF
    -0.64
    WebServlet
    -0.54
    WritableDatabase
    -0.51
    AccessFile
    -0.51
    دانشنامهٔ
    -0.51
    RunWith
    -0.50
     متحده
    -0.49
    AutoScale
    -0.49
    POSITIVE LOGITS
     lemma
    0.89
     Lemma
    0.81
     theorem
    0.81
    lemma
    0.79
     lemmas
    0.77
     proof
    0.77
     corollary
    0.77
     Theorem
    0.76
     lema
    0.73
    Lemma
    0.73
    Activations Density 1.883%

    No Known Activations