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

    Neuronpedia

    Jacobian LensNEW
    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. 22-GEMMASCOPE-RES-16K
    11. 3202
    Prev
    Next
    INDEX
    Explanations

    numerical quantities and statistics

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

    Fractions (thirds, fifths, half)

    np_acts-logits-general · gemini-2.0-flash

    Fractions and ordinals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kaynağından
    -0.49
    قایناق‌لار
    -0.47
     <<<<<<<<<<<<<<
    -0.46
     leksikon
    -0.44
     encara
    -0.44
    RepeatedField
    -0.43
    PropertyChanging
    -0.43
    mybatisplus
    -0.42
     réflex
    -0.41
    گانی
    -0.41
    POSITIVE LOGITS
     thirds
    0.87
     third
    0.82
     fifth
    0.81
     fourth
    0.79
    third
    0.78
    Third
    0.76
     Third
    0.75
     FIFTH
    0.75
     ninth
    0.73
    fifth
    0.73
    Activations Density 0.558%

    No Known Activations