Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 13983
    Prev
    Next
    INDEX
    Explanations

    instances of personal pronouns and first-person references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Obrázky
    -0.85
    
    -0.79
     externi
    -0.73
     AssemblyTitle
    -0.71
     <<<<<<<<<<<<<<
    -0.70
     autorytatywna
    -0.62
    ագրություններ
    -0.61
    AutoScaleMode
    -0.61
     للمعارف
    -0.60
    GEBURTSDATUM
    -0.59
    POSITIVE LOGITS
     automatiques
    0.50
     Galer
    0.49
    cyjnych
    0.47
    akala
    0.47
     itſelf
    0.47
    ioka
    0.47
     ček
    0.46
     Quakers
    0.46
     manuell
    0.45
    thee
    0.45
    Activations Density 0.576%

    No Known Activations