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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 33369
    Prev
    Next
    INDEX
    Explanations

    terms related to user interface elements and component interactions in web development

    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
    ########.
    -0.57
     BoxFit
    -0.55
    majánló
    -0.53
    corsi
    -0.53
    ocities
    -0.51
    lichung
    -0.51
    ◳
    -0.50
    wifery
    -0.50
    Bakgrunns
    -0.50
     виправивши
    -0.49
    POSITIVE LOGITS
    dropdown
    0.86
    IntoConstraints
    0.75
    menuStrip
    0.54
    PIPE
    0.40
     dropdown
    0.40
    Personendaten
    0.40
    PreExecute
    0.38
    Халык
    0.35
    bitField
    0.32
    exitRule
    0.32
    Activations Density 0.001%

    No Known Activations