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. 130023
    Prev
    Next
    INDEX
    Explanations

    features related to mobile app functionalities and settings

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

    settings, features and options

    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
     contemporáneo
    -0.37
     decoracion
    -0.32
     fær
    -0.30
    теров
    -0.30
     lejos
    -0.30
     acquisition
    -0.30
     piattaforma
    -0.30
     inoxidable
    -0.29
     contemporain
    -0.29
     Chief
    -0.29
    POSITIVE LOGITS
    VIAF
    0.71
    OGND
    0.68
     shortcuts
    0.65
    脚注の使い方
    0.64
    出版年
    0.63
    ="@+
    0.63
     محفوظة
    0.62
    afficheront
    0.62
     emojis
    0.62
     wallpapers
    0.60
    Activations Density 0.049%

    No Known Activations