© 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. 4-GEMMASCOPE-RES-16K
    11. 3879
    Prev
    Next
    INDEX
    Explanations

    references to the term "Su" and related variations, indicating a focus on specific names or categories associated with that prefix

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.85
    మూ
    -0.63
     Hald
    -0.62
    },"
    -0.62
    $.\\
    -0.61
    ẵn
    -0.61
    ."]
    -0.61
    +:+
    -0.60
     Kamen
    -0.60
    VideoCapture
    -0.59
    POSITIVE LOGITS
     Su
    2.49
    Su
    2.42
     su
    2.21
    su
    2.09
     SU
    1.97
    SU
    1.71
     Suzy
    1.42
     Sutherland
    1.28
     Су
    1.22
     Suf
    1.20
    Activations Density 0.106%

    No Known Activations