© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2869
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and recognition towards individuals and organizations for their contributions

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

    Expressing gratitude or thanks

    np_acts-logits-general · gemini-2.0-flash

    thanking specific people or groups

    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
    Согласно
    -0.59
     getItemId
    -0.59
     iirc
    -0.58
    WithIOException
    -0.56
    ByVersion
    -0.55
    האם
    -0.51
     depending
    -0.51
     purposes
    -0.50
    identical
    -0.50
     Depending
    -0.49
    POSITIVE LOGITS
     thank
    1.00
     THANK
    0.94
     especially
    0.91
    especially
    0.85
     Thank
    0.84
     🙏
    0.84
    THANK
    0.83
     especialmente
    0.81
    thank
    0.78
     wonderful
    0.78
    Activations Density 0.185%

    No Known Activations