© 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. 23-GEMMASCOPE-RES-16K
    11. 14792
    Prev
    Next
    INDEX
    Explanations

    content related to scientific or mathematical topics, particularly focusing on equations or formulae and their variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    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
    -0.85
    B
    -0.81
    getB
    -0.79
     b
    -0.78
    bcrypt
    -0.72
     BUREAU
    -0.72
    beta
    -0.72
    bc
    -0.72
     B
    -0.72
    ʙ
    -0.72
    POSITIVE LOGITS
    couz
    0.51
    twimg
    0.48
     geleverd
    0.42
    üsseldorf
    0.37
    ésia
    0.37
    Tikang
    0.37
     Atiku
    0.35
    ersdorf
    0.35
     arşivlendi
    0.35
    ########.
    0.35
    Activations Density 1.038%

    No Known Activations