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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 8406
    Prev
    Next
    INDEX
    Explanations

    terms related to fonts and typesetting in programming and design contexts

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

    File paths or references to files

    np_acts-logits-general · gemini-2.0-flash

    world class, world-leading, world-renowned

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.90
    ########.
    -0.62
    findpost
    -0.61
    IsContent
    -0.57
    ollectionView
    -0.54
     betweenstory
    -0.54
     Vikipedi
    -0.53
    noons
    -0.53
    })();
    -0.52
    ngdoc
    -0.51
    POSITIVE LOGITS
     հղումներ
    0.51
    Referensi
    0.47
     خارجية
    0.46
    তথ্যসূত্র
    0.45
     Беларусь
    0.45
     Dis
    0.45
     دریافت‌شده
    0.44
    dis
    0.43
     Reverse
    0.42
    Dis
    0.42
    Activations Density 0.607%

    No Known Activations