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. 69562
    Prev
    Next
    INDEX
    Explanations

    chemical elements and compounds related to health and environmental studies

    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
     natural
    -0.39
    tahankan
    -0.37
     samlet
    -0.34
    enumi
    -0.34
     Entsch
    -0.34
     mest
    -0.34
    HMAC
    -0.33
    ↵↵
    -0.33
    }
    -0.33
    šanai
    -0.32
    POSITIVE LOGITS
     Walkover
    0.76
     typelib
    0.73
     queſta
    0.71
    BeginInit
    0.68
     IBOutlet
    0.66
    ResumeLayout
    0.66
     betweenstory
    0.62
    EndInit
    0.61
    majánló
    0.60
    ніципалі
    0.60
    Activations Density 0.246%

    No Known Activations