© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 5137
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation related to conditions or assumptions in formal proofs

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

    after asterisks

    np_acts-logits-general · gemini-2.0-flash

    lemmas, theorems, assumptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HtmlAttribute
    -0.31
     izan
    -0.29
     szcz
    -0.29
     pilas
    -0.28
     delgada
    -0.28
     saling
    -0.27
     formación
    -0.27
     συγκ
    -0.26
    SpringRunner
    -0.26
     rest
    -0.26
    POSITIVE LOGITS
    verwijspagina
    0.72
    المناصب
    0.70
    IsContent
    0.68
    ScopeManager
    0.66
    Jeografia
    0.63
    RTLR
    0.63
     EconPapers
    0.63
    sbericht
    0.62
     esternos
    0.61
     transfieras
    0.60
    Activations Density 0.067%

    No Known Activations