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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 68671
    Prev
    Next
    INDEX
    Explanations

    medical procedures and techniques related to surgical interventions

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

    approach, execute, block, expose

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    shutil
    -0.30
     adapt
    -0.27
    тельность
    -0.27
    })));
    -0.26
    AdapterView
    -0.25
     adapta
    -0.25
     Caterpillar
    -0.25
    촉
    -0.25
     adatt
    -0.25
     oran
    -0.25
    POSITIVE LOGITS
    webElementXpaths
    0.77
     otomatig
    0.75
     كومونز
    0.71
    NameInMap
    0.70
    IntoConstraints
    0.65
     ffilmiau
    0.60
    原始内容存档于
    0.60
    sizeCache
    0.59
    Зноскі
    0.58
    URLException
    0.57
    Activations Density 0.181%

    No Known Activations