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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 4212
    Prev
    Next
    INDEX
    Explanations

    references to the online context or platform usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SwiftUI
    -0.66
    styleType
    -0.61
    JsonProperty
    -0.61
     requestCode
    -0.60
    ètres
    -0.60
     Bets
    -0.58
     Gry
    -0.58
     Garrison
    -0.58
    bandcamp
    -0.58
     resultCode
    -0.56
    POSITIVE LOGITS
    ONLINE
    1.20
     ONLINE
    1.20
     Online
    1.15
     online
    1.15
    offline
    1.10
    Online
    1.08
    online
    1.06
     offline
    1.06
    ſelves
    1.02
    Offline
    1.01
    Activations Density 0.042%

    No Known Activations