© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1685
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditional statements and conclusions in mathematical 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
    AsUp
    -0.77
    openzeppelin
    -0.53
     jälkeen
    -0.51
    ++);
    -0.49
     dimana
    -0.49
     noires
    -0.48
     borracha
    -0.48
    --){
    -0.47
    Where
    -0.46
    --)
    -0.46
    POSITIVE LOGITS
     Eq
    0.97
     Equation
    0.89
     Theorem
    0.79
     Definition
    0.76
     Eqs
    0.76
     Proposition
    0.72
     equation
    0.72
     eqn
    0.71
     eq
    0.70
     Corollary
    0.68
    Activations Density 3.195%

    No Known Activations