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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12757
    Prev
    Next
    INDEX
    Explanations

    medical trials and their related outcomes

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

    Decreased/increased, followed by a medical effect

    np_acts-logits-general · gemini-2.0-flash

    adenocarcinoma, survival outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beziehungs
    -0.39
     nemlig
    -0.37
     nämlich
    -0.36
    最为
    -0.36
    什么呢
    -0.33
     namelijk
    -0.31
     proprement
    -0.31
     itself
    -0.31
     tranſ
    -0.31
     například
    -0.30
    POSITIVE LOGITS
    XmlAccessType
    0.67
    complexContent
    0.66
     <<<<<<<<<<<<<<
    0.63
    webElementXpaths
    0.62
    +#+#
    0.60
     }{@
    0.60
    nsics
    0.58
    Hentet
    0.58
    rungsseite
    0.57
    bbean
    0.57
    Activations Density 0.844%

    No Known Activations