© 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. 12-GEMMASCOPE-RES-16K
    11. 339
    Prev
    Next
    INDEX
    Explanations

    references to articles and supplementary material in academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •temp

    No Comments

    Negative Logits
     itſelf
    -0.76
    Зноскі
    -0.70
     برانيه
    -0.65
     يتيمه
    -0.65
    yarnpkg
    -0.64
    gonic
    -0.64
     autorytatywna
    -0.63
     themſelves
    -0.61
     חיצוניים
    -0.61
     harte
    -0.60
    POSITIVE LOGITS
    NameInMap
    0.66
    CppMethod
    0.65
    GeneratedValue
    0.61
    springer
    0.56
    ("")]
    0.52
    DataAnnotations
    0.52
    JoinColumn
    0.49
     Springer
    0.46
    ANTLR
    0.45
     en
    0.45
    Activations Density 0.178%

    No Known Activations