© 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. 18-GEMMASCOPE-RES-16K
    11. 4400
    Prev
    Next
    INDEX
    Explanations

    mixed terms related to medical conditions and automotive brands

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

    "Toyota" and ulcer-related words

    np_acts-logits-general · gemini-2.0-flash

    Toyota and ulcers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hless
    -0.59
     resourceCulture
    -0.56
     pleaſure
    -0.55
     typelib
    -0.53
     Fing
    -0.52
    BufferException
    -0.51
    SharedDtor
    -0.51
     ſever
    -0.50
    astéroïdes
    -0.49
    andle
    -0.49
    POSITIVE LOGITS
     Toyota
    1.12
    Toyota
    0.98
     toyota
    0.96
     Tacoma
    0.86
    toyota
    0.82
    TOY
    0.81
     TOY
    0.79
     Tundra
    0.73
     Corolla
    0.70
     Toy
    0.70
    Activations Density 0.198%

    No Known Activations