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

    Neuronpedia

    Jacobian LensNEW
    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. 12-GEMMASCOPE-RES-16K
    11. 13136
    Prev
    Next
    INDEX
    Explanations

    academic phrases and structures that denote formal proofs or theorems in a mathematical context

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

    references to theorems, lemmas, and propositions in mathematical text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    formal mathematical exposition cues in academic papers, especially statements and references to theorems, lemmas, propositions, sections, and proofs.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     giornal
    -0.46
    WireFormatLite
    -0.41
    一番
    -0.38
    ]+$
    -0.37
     منظ
    -0.36
     panor
    -0.36
     vapors
    -0.36
     visitó
    -0.36
     Ment
    -0.36
     Pitts
    -0.36
    POSITIVE LOGITS
    Theorem
    0.99
    THEOREM
    0.92
    Corollary
    0.86
     theorem
    0.84
     Theorem
    0.83
    Lemma
    0.80
    theorem
    0.79
     theorems
    0.68
     AssemblyCulture
    0.66
     StatelessWidget
    0.65
    Activations Density 1.046%

    No Known Activations