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. 13-GEMMASCOPE-RES-16K
    6. 6778
    Prev
    Next
    INDEX
    Explanations

    specific formatting or coding symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Spie
    -0.81
     VIAF
    -0.73
    uyasha
    -0.72
    ь
    -0.70
    skjaer
    -0.70
    /**
    -0.70
    VIAF
    -0.69
    p
    -0.68
     devriez
    -0.68
    AdapterView
    -0.67
    POSITIVE LOGITS
     welcome
    1.73
     welcomed
    1.58
     welcoming
    1.53
     Welcome
    1.48
    welcome
    1.46
     WELCOME
    1.46
    elcome
    1.45
     welcomes
    1.44
    WELCOME
    1.40
    Welcome
    1.39
    Activations Density 0.057%

    No Known Activations