© 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. 3826
    Prev
    Next
    INDEX
    Explanations

    important geographical features and their characteristics

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

    bodies of water

    np_acts-logits-general · gemini-2.0-flash

    bodies of water

    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
     protoimpl
    -0.53
    RTDA
    -0.49
    diğini
    -0.48
    Root
    -0.46
    SharedCtor
    -0.46
     clothe
    -0.45
    秆
    -0.45
    روط
    -0.45
     referrerpolicy
    -0.45
    ernalia
    -0.45
    POSITIVE LOGITS
     lake
    1.68
     lakes
    1.49
     Lake
    1.42
     waters
    1.38
    Lake
    1.33
     pond
    1.33
     ponds
    1.26
    lake
    1.25
     LAKE
    1.24
     water
    1.21
    Activations Density 0.206%

    No Known Activations