© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 4248
    Prev
    Next
    INDEX
    Explanations

    terms related to biological processes and scientific research, particularly in the context of health and medicine

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

    or characters followed by "tion" or "tual"

    np_acts-logits-general · gemini-2.0-flash

    counterfactuals and colonization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.87
    -
    -0.79
     EconPapers
    -0.75
    .
    -0.71
     (
    -0.71
    ிகள்
    -0.64
     se
    -0.63
     des
    -0.62
     себе
    -0.61
     
    -0.61
    POSITIVE LOGITS
     iſt
    1.11
    ſtra
    1.07
    ſem
    1.07
     Eſ
    1.04
     BRARY
    1.03
     ſind
    1.03
     Anſ
    1.02
    ſelves
    1.01
    IBLIO
    0.99
    thodon
    0.98
    Activations Density 1.297%

    No Known Activations