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. 20-GEMMASCOPE-RES-131K
    6. 90113
    Prev
    Next
    INDEX
    Explanations

    terms related to industries and their operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    Angebot
    -0.36
     Verhältnisse
    -0.35
     Einrichtungen
    -0.35
     zetten
    -0.35
    ISupport
    -0.35
     lease
    -0.35
    AccessFile
    -0.35
    anstalt
    -0.34
     zien
    -0.33
    crollView
    -0.32
    POSITIVE LOGITS
    +#+#
    0.64
     Injectable
    0.62
     roaming
    0.61
     mobile
    0.60
    mobiles
    0.58
     mobiles
    0.58
    mobile
    0.57
     mobilen
    0.56
     nomadic
    0.56
     travelling
    0.53
    Activations Density 0.311%

    No Known Activations