Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 13968
    Prev
    Next
    INDEX
    Explanations

    references to historic preservation and archaeological research efforts

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

    archaeology or historical preservation

    np_acts-logits-general · gemini-2.0-flash

    archaeologists and historical preservation

    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
    sizeCache
    -0.58
    новниш
    -0.55
    Handlung
    -0.54
     виправивши
    -0.53
    StructEnd
    -0.52
     SwitchCompat
    -0.50
    Derbyniad
    -0.50
    MetaType
    -0.49
     gynhyrchwyd
    -0.48
    GEBURTS
    -0.48
    POSITIVE LOGITS
     archaeological
    1.46
     archaeologists
    1.44
     archaeology
    1.39
     archaeologist
    1.39
    Archae
    1.33
     historians
    1.31
     archeological
    1.31
    archae
    1.29
     Archaeology
    1.28
     Archaeological
    1.27
    Activations Density 0.321%

    No Known Activations