© 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. 16-GEMMASCOPE-RES-16K
    11. 2674
    Prev
    Next
    INDEX
    Explanations

    phrases indicating validation or proof of concepts

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

    Sentences containing "prove" or "proven"

    np_acts-logits-general · gemini-2.0-flash

    establishes truth or effectiveness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Geist
    -0.61
    día
    -0.56
    瘩
    -0.56
    OCCURRED
    -0.55
    dataclass
    -0.55
    awtextra
    -0.53
    Controllo
    -0.53
     okuyayım
    -0.53
    dziew
    -0.51
    LikeLike
    -0.50
    POSITIVE LOGITS
     prove
    1.29
     Prove
    1.22
     proves
    1.19
    Prove
    1.16
     proved
    1.14
     proving
    1.13
    prove
    1.00
     Proving
    1.00
     proofs
    0.85
     proven
    0.83
    Activations Density 0.170%

    No Known Activations