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
    4. Residual Stream - 131k
    5. 32-GEMMASCOPE-RES-131K
    6. 129997
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and technical syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numbers with ±

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_32/width_131k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.32.hook_resid_post
    Hook Layer
    32
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mbggenerated
    -0.37
    extendable
    -0.34
    urized
    -0.34
    urable
    -0.33
     consigo
    -0.32
    륭
    -0.31
     못
    -0.31
     venía
    -0.31
     distanciation
    -0.31
    PointerException
    -0.30
    POSITIVE LOGITS
     يتيمه
    0.77
     disambiguazione
    0.68
    bootstrapcdn
    0.60
    
    0.52
    évaluateur
    0.51
     ویکی‌پدی
    0.48
    +#+#
    0.48
     VIDEOTAPE
    0.47
    لينكات
    0.47
    Gigi
    0.47
    Activations Density 0.060%

    No Known Activations