© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14738
    Prev
    Next
    INDEX
    Explanations

    references to spiritual purification and the necessity of faith in achieving salvation

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

    Followed by a form of "to be"

    np_acts-logits-general · gemini-2.0-flash

    we are, must examine, to be

    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
    Initializable
    -0.54
    ImageContext
    -0.54
     skr
    -0.50
     Sicilian
    -0.47
    Schedulers
    -0.47
     Automat
    -0.45
     haunting
    -0.45
     condensation
    -0.45
     factorization
    -0.45
    cond
    -0.45
    POSITIVE LOGITS
     يتيمه
    0.61
     fas
    0.60
    DoubleQuotes
    0.60
     pray
    0.60
     minister
    0.59
    oa̍t
    0.58
     kasarigan
    0.55
     <>",
    0.55
     prayed
    0.55
     estekak
    0.55
    Activations Density 0.237%

    No Known Activations