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. 6008
    Prev
    Next
    INDEX
    Explanations

    words and concepts related to technology and structure

    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
    Diweddarwch
    -0.51
     ModelExpression
    -0.47
    isiaj
    -0.47
     Infórmanos
    -0.47
     못
    -0.43
    今日
    -0.43
    LookAnd
    -0.43
    UserScript
    -0.43
     gynhyrchwyd
    -0.43
     ***!
    -0.42
    POSITIVE LOGITS
    ibatis
    0.44
    icale
    0.42
    ########.
    0.41
     المعيارى
    0.40
     CURIAM
    0.39
     maestra
    0.39
    SOUNDBITE
    0.39
     Савезне
    0.39
    Билгалдахарш
    0.39
    TECHNOLOGY
    0.38
    Activations Density 0.024%

    No Known Activations