© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 13092
    Prev
    Next
    INDEX
    Explanations

    instructions related to energy efficiency and safety measures

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

    Recommendations, suggestions, or instructions

    np_acts-logits-general · gemini-2.0-flash

    preferably: optimal choice

    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
    ďaka
    -0.65
    原始内容存档于
    -0.61
     précieux
    -0.58
    incredible
    -0.57
     unprecedented
    -0.57
    Unnamed
    -0.54
     dangereux
    -0.54
     devoir
    -0.53
    enseignements
    -0.53
    nowu
    -0.52
    POSITIVE LOGITS
     preferably
    1.21
    preferably
    1.10
     adequate
    0.98
     appropriate
    0.98
     good
    0.92
     atleast
    0.91
     préférence
    0.91
     suitable
    0.90
     Preferably
    0.89
     möglichst
    0.89
    Activations Density 0.360%

    No Known Activations