© 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. 21-GEMMASCOPE-RES-16K
    11. 8999
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to definitions and descriptions in various contexts, particularly in scientific or technical fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     béné
    -0.53
     merve
    -0.47
     genoux
    -0.46
     rayures
    -0.46
     Partager
    -0.45
     grunn
    -0.45
    Theorem
    -0.44
     eficientes
    -0.44
     liné
    -0.43
     πραγ
    -0.43
    POSITIVE LOGITS
     referring
    1.18
     interchangeably
    1.05
     synonymous
    1.04
     synonym
    1.03
     connotations
    1.00
     used
    0.99
     synonyms
    0.98
     connotation
    0.98
     coined
    0.94
     refer
    0.92
    Activations Density 0.395%

    No Known Activations