© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 8694
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions, particularly those used in equations and functions

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

    Token followed by "B"

    np_acts-logits-general · gemini-2.0-flash

    B followed by B

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     b
    -0.89
    b
    -0.71
    reggio
    -0.48
    Ь
    -0.45
    ƅ
    -0.44
    Ƅ
    -0.44
    𝗯
    -0.42
     ویکی‌پدیای
    -0.41
    extAlignment
    -0.40
    ｂ
    -0.40
    POSITIVE LOGITS
     BB
    0.94
     Ба
    0.91
    Ｂ
    0.91
     Bo
    0.91
     Ba
    0.90
     Be
    0.89
     Bi
    0.89
     Бо
    0.88
     Bl
    0.87
    BB
    0.87
    Activations Density 0.574%

    No Known Activations