© 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. 6152
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving derivatives and functions

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

    Mathematical deductions and logical conclusions

    np_acts-logits-general · gemini-2.0-flash

    mathematical conclusions

    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
    Nonnull
    -0.50
    ừng
    -0.45
     Frü
    -0.44
     Gré
    -0.44
     Fren
    -0.44
    czegó
    -0.43
    เทศ
    -0.43
     Irán
    -0.42
    rzysz
    -0.42
    шке
    -0.41
    POSITIVE LOGITS
     therefore
    1.30
     Therefore
    1.26
    therefore
    1.23
    Therefore
    1.22
     Thus
    1.13
    Thus
    1.07
     Hence
    1.07
     thus
    1.06
     hence
    1.02
    Hence
    1.02
    Activations Density 1.850%

    No Known Activations