© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 14-GEMMASCOPE-RES-16K
    11. 286
    Prev
    Next
    INDEX
    Explanations

    technical language and terminology related to medical or scientific measurements and assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pues
    -0.54
     fubject
    -0.52
    Pues
    -0.46
     purpoſe
    -0.46
    TypeDef
    -0.45
     moistened
    -0.44
     cartaz
    -0.43
     reaſon
    -0.43
     vaz
    -0.43
    Vla
    -0.42
    POSITIVE LOGITS
    PullParser
    0.66
    chtenstein
    0.66
     تعدى
    0.66
    NOPQRST
    0.65
    ItemBackground
    0.62
    ándor
    0.61
    اعمال
    0.61
    CppCodeGen
    0.60
    amaran
    0.59
     FontFamily
    0.58
    Activations Density 0.834%

    No Known Activations