© 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. 5-GEMMASCOPE-RES-16K
    11. 5571
    Prev
    Next
    INDEX
    Explanations

    technical terms and proper nouns related to computer science, medicine, or academia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.50
    oredCriteria
    -0.49
    ಃ
    -0.46
    ValueGeneration
    -0.46
    طلحات
    -0.43
    Outro
    -0.42
     dro
    -0.41
     guarn
    -0.41
    ندن
    -0.41
    milla
    -0.41
    POSITIVE LOGITS
    CloseOperation
    0.81
    EndContext
    0.74
    ViewFeatures
    0.73
     насељу
    0.71
     LUMP
    0.70
    ########.
    0.66
     esternos
    0.66
     članak
    0.64
    ::_('
    0.63
    <?
    0.63
    Activations Density 2.360%

    No Known Activations