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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12513
    Prev
    Next
    INDEX
    Explanations

    phrases related to cooperation and collaboration among mechanisms or therapies

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

    preceding medical treatments or diagnostic terms

    np_acts-logits-general · gemini-2.0-flash

    combining or supplementing therapies

    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
    httphttps
    -0.60
     مشين
    -0.57
     IBOutlet
    -0.54
    PostBack
    -0.49
    ∬
    -0.49
    lime
    -0.47
    RectangleBorder
    -0.47
    undrum
    -0.47
    databind
    -0.46
    crombie
    -0.46
    POSITIVE LOGITS
     complé
    0.42
     supplementing
    0.41
     complément
    0.41
     supplemented
    0.40
     supplement
    0.39
     complement
    0.38
    featureID
    0.38
     فريبيس
    0.37
    supplement
    0.36
    RTSN
    0.36
    Activations Density 0.613%

    No Known Activations