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. 6001
    Prev
    Next
    INDEX
    Explanations

    keywords related to modal dialog interactions and actions

    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
     utafitiHapana
    -0.46
     relief
    -0.29
     era
    -0.29
     merk
    -0.29
    υμα
    -0.28
     казалось
    -0.28
    xue
    -0.28
     envy
    -0.28
     stav
    -0.27
    })));
    -0.27
    POSITIVE LOGITS
     MatDialog
    1.00
    DialogComponent
    0.74
    sidemargin
    0.70
     ब्रेकडाउन
    0.61
    AnchorTagHelper
    0.59
    tagext
    0.58
    IndentedString
    0.58
    Jereo
    0.57
    execSQL
    0.57
     ddelweddau
    0.57
    Activations Density 0.003%

    No Known Activations