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. 105150
    Prev
    Next
    INDEX
    Explanations

    gene expression and variation in viruses

    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
    #+#
    -0.51
    AnchorStyles
    -0.49
    Биография
    -0.45
     ویکی‌پدیای
    -0.44
    hyrchwyd
    -0.44
     ThemeData
    -0.40
    RTHOOK
    -0.39
     purpoſe
    -0.38
     للاسماء
    -0.38
     poffible
    -0.37
    POSITIVE LOGITS
     Савезне
    0.52
    tonode
    0.44
    skine
    0.43
     nonUne
    0.41
     plufieurs
    0.41
     jaula
    0.41
     grotte
    0.41
     preghiera
    0.40
     espirituales
    0.40
     Schluß
    0.40
    Activations Density 0.015%

    No Known Activations