© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 6522
    Prev
    Next
    INDEX
    Explanations

    phrases and terms indicating assistance or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IBarButtonItem
    -0.76
    GEBURTSDATUM
    -0.75
     Rig
    -0.75
     Wally
    -0.74
    يبة
    -0.72
     Tand
    -0.69
     Eres
    -0.69
    anair
    -0.69
    PreferredItem
    -0.69
     mã
    -0.68
    POSITIVE LOGITS
     help
    2.07
    help
    1.91
     helps
    1.87
     Help
    1.79
     helping
    1.78
     HELP
    1.77
    Help
    1.75
    HELP
    1.75
    helps
    1.73
    Helps
    1.72
    Activations Density 0.068%

    No Known Activations