© 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. 10590
    Prev
    Next
    INDEX
    Explanations

    proper nouns and culturally significant terms

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

    Appears at the beginning of a line of text

    np_acts-logits-general · gemini-2.0-flash

    Turkmen cities or technical keywords

    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
    matchCondition
    -0.60
    ájá
    -0.58
    uminen
    -0.56
    áját
    -0.56
    ADORA
    -0.54
    uxxxx
    -0.53
     AMOR
    -0.51
    IndentedString
    -0.50
     NDEBUG
    -0.50
    ttino
    -0.48
    POSITIVE LOGITS
     dépens
    0.53
     âmes
    0.48
     chrétiens
    0.47
     cœurs
    0.47
     supérieurs
    0.46
     reç
    0.45
     entrevist
    0.44
     travailleurs
    0.44
     engraçadas
    0.44
     armées
    0.43
    Activations Density 0.028%

    No Known Activations