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. 91144
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to programming functions and error handling

    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
    windowFixed
    -0.47
     Wikimedijinoj
    -0.41
    intios
    -0.40
    calaure
    -0.40
    újo
    -0.40
    httphttps
    -0.40
    戬
    -0.39
    espejo
    -0.36
    colgante
    -0.35
    istoitu
    -0.35
    POSITIVE LOGITS
     صوتيه
    0.57
    parency
    0.48
    MessageTagHelper
    0.48
    Компания
    0.48
    zom
    0.48
     ainfi
    0.47
    MigrationBuilder
    0.46
    DMETHOD
    0.46
    UnsafeEnabled
    0.46
    halo
    0.45
    Activations Density 0.218%

    No Known Activations