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. 23465
    Prev
    Next
    INDEX
    Explanations

    critical factors and aspects related to decision-making and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    RectangleBorder
    -0.64
     مرئيه
    -0.63
    uxxxx
    -0.60
     PopupWindow
    -0.60
     للمعارف
    -0.59
     Exacts
    -0.54
    WillAppear
    -0.54
     MenuView
    -0.53
     ExecuteAsync
    -0.53
     Gegenteil
    -0.51
    POSITIVE LOGITS
     caché
    0.31
     henvisninger
    0.31
    .~(\
    0.31
    didSet
    0.31
     Hauser
    0.30
    kräf
    0.29
     față
    0.29
     kun
    0.29
    forhold
    0.29
     attraction
    0.29
    Activations Density 0.073%

    No Known Activations