© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15347
    Prev
    Next
    INDEX
    Explanations

    HTML elements and attributes related to linking and referencing

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

    HTML tags: div, a, ul

    np_acts-logits-general · gemini-2.0-flash

    html tag followed by attribute

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     steam
    -0.49
     Ror
    -0.45
    agic
    -0.44
     Abonnez
    -0.42
     stie
    -0.42
     Tierney
    -0.42
     sentinel
    -0.41
     Steam
    -0.41
     SSR
    -0.41
    щото
    -0.41
    POSITIVE LOGITS
    Datuak
    0.99
     незавершена
    0.82
    findpost
    0.76
    OGND
    0.72
     Мексичка
    0.71
     تضيفلها
    0.71
     Roskov
    0.70
    saraba
    0.69
    XmlAccessType
    0.65
    новниш
    0.65
    Activations Density 0.074%

    No Known Activations