© 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. 3-GEMMASCOPE-RES-16K
    11. 140
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to biology and bioengineering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hű
    -0.43
    martial
    -0.42
     bandera
    -0.41
     bandeira
    -0.39
     cuivre
    -0.39
     полка
    -0.39
     avantage
    -0.38
    </td>
    -0.38
     totalmente
    -0.38
    淋
    -0.38
    POSITIVE LOGITS
     виправивши
    0.90
    RuleContext
    0.85
    memoized
    0.84
     Normdatei
    0.83
    styleType
    0.82
     imageNamed
    0.81
     <>",
    0.80
    انيف
    0.79
    verwijspagina
    0.78
    NUMX
    0.77
    Activations Density 1.656%

    No Known Activations