© 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. 8806
    Prev
    Next
    INDEX
    Explanations

    mentions of hunting equipment and safety concerns related to it

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

    associated with archery

    np_acts-logits-general · gemini-2.0-flash

    bow and arrow

    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
    +#+
    -0.62
    لیس
    -0.54
    esModule
    -0.54
    __':
    -0.51
    HostException
    -0.49
    Tembelea
    -0.49
     estimés
    -0.49
     Cott
    -0.48
    VOLUME
    -0.48
    GEBURTSDATUM
    -0.48
    POSITIVE LOGITS
     bow
    1.66
     arrow
    1.56
     arrows
    1.56
     bows
    1.50
     Bow
    1.47
    bow
    1.42
    Bow
    1.36
     Arrow
    1.34
    bows
    1.31
     Arrows
    1.28
    Activations Density 0.122%

    No Known Activations