© 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. 10250
    Prev
    Next
    INDEX
    Explanations

    technological advancements related to medical devices and innovations

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

    Followed by "using" or "with"

    np_acts-logits-general · gemini-2.0-flash

    by-products, processes, and tools

    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
     complètes
    -0.60
     olsun
    -0.58
    localctx
    -0.58
     pior
    -0.57
    \{\\
    -0.57
     loisirs
    -0.57
    Sucesor
    -0.56
     adultes
    -0.54
     demais
    -0.53
    saraba
    -0.53
    POSITIVE LOGITS
     special
    1.43
     specially
    1.38
     спеціаль
    1.22
    special
    1.22
     specjal
    1.22
     speciale
    1.20
     specialized
    1.19
    specially
    1.13
     специаль
    1.11
    specialized
    1.05
    Activations Density 0.797%

    No Known Activations