Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 3460
    Prev
    Next
    INDEX
    Explanations

    references to the chemical compound "ana" and its related forms or contexts in various scientific discussions

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

    preceding or containing "ana"

    np_acts-logits-general · gemini-2.0-flash

    Anesthesia/anabolic/anemia related

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MENAFN
    -0.50
    OPC
    -0.48
    os
    -0.48
    thaf
    -0.48
    )++;
    -0.48
    ysaccharides
    -0.46
    MNA
    -0.46
    queryInterface
    -0.46
    spricht
    -0.45
    icago
    -0.45
    POSITIVE LOGITS
    arXiv
    1.10
     CreateTagHelper
    0.96
     propOrder
    0.77
    expandindo
    0.76
    Geplaatst
    0.71
    WebElementEntity
    0.68
     مرئيه
    0.67
    abestanden
    0.65
    +#+
    0.64
    الدراسه
    0.63
    Activations Density 0.263%

    No Known Activations