© 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. 6733
    Prev
    Next
    INDEX
    Explanations

    specific structured elements related to scientific research or data presentation

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

    Appears before two capital letters

    np_acts-logits-general · gemini-2.0-flash

    words starting with J followed by t

    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
     AssemblyCulture
    -0.51
    BeginContext
    -0.50
    PreferredItem
    -0.45
    RenderAtEndOf
    -0.43
     للغ
    -0.43
     المعيارى
    -0.43
    Pranala
    -0.40
    Билгалдахарш
    -0.40
    Ārējās
    -0.40
     Dostupné
    -0.40
    POSITIVE LOGITS
     JJ
    1.26
     JT
    1.19
     JP
    1.18
     JC
    1.17
     JO
    1.16
    JS
    1.15
    JE
    1.15
     JB
    1.15
    JA
    1.15
    JC
    1.15
    Activations Density 1.742%

    No Known Activations