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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3494
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or geographical features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Roads, trails, lines, and pathways

    np_acts-logits-general · gemini-2.0-flash

    routes connecting and continuing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    UnsafeEnabled
    -0.63
    iseite
    -0.57
    billed
    -0.54
     groots
    -0.51
    Попис
    -0.51
    phère
    -0.50
    gestellt
    -0.49
    nóstico
    -0.47
     nakalista
    -0.47
    urangan
    -0.46
    POSITIVE LOGITS
     connecting
    1.05
     passing
    0.90
     linking
    0.90
     crossing
    0.90
     connects
    0.84
    connecting
    0.79
     branching
    0.76
     routes
    0.76
     originating
    0.74
     connect
    0.73
    Activations Density 0.365%

    No Known Activations