© 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. 4825
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and references related to research and development in various fields

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

    Follows "Tab" or "tab" (often in UI contexts)

    np_acts-logits-general · gemini-2.0-flash

    tab control selection

    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
    ASS
    -0.80
     ASS
    -0.79
    ass
    -0.79
    AS
    -0.78
     ass
    -0.78
    ASF
    -0.76
     ASH
    -0.75
    ASU
    -0.72
    ASH
    -0.72
     ASM
    -0.72
    POSITIVE LOGITS
    ◀
    0.47
    alik
    0.42
     Tabor
    0.41
    DataAdapter
    0.41
     Matta
    0.39
    hibi
    0.39
     Calhoun
    0.39
     Charlton
    0.39
    ReadInt
    0.38
     Cheek
    0.38
    Activations Density 1.244%

    No Known Activations