© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 3063
    Prev
    Next
    INDEX
    Explanations

    elements related to file management and updates in software applications

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

    Tokens followed by prepositions or punctuation

    np_acts-logits-general · gemini-2.0-flash

    easily or perfectly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ärsk
    -0.42
    ニューアル
    -0.38
     możli
    -0.38
    を中心
    -0.38
     الاحتلال
    -0.37
     unintentional
    -0.37
    shall
    -0.37
     moeten
    -0.36
     tended
    -0.36
     Shall
    -0.36
    POSITIVE LOGITS
     fácilmente
    0.98
     easily
    0.96
     facilmente
    0.84
    easily
    0.84
     anytime
    0.72
     Easily
    0.69
    Easily
    0.68
     perfectamente
    0.66
     facilement
    0.66
     tranquila
    0.64
    Activations Density 0.586%

    No Known Activations