© 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. 7-GEMMASCOPE-RES-16K
    11. 6514
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "DOI," which signifies digital object identifiers for academic articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    請繼續往下閱讀
    -0.55
     Rachael
    -0.50
     consigo
    -0.50
    Lähteet
    -0.48
    TTY
    -0.47
    sty
    -0.46
    Portail
    -0.46
     tức
    -0.45
    artney
    -0.45
    assembly
    -0.44
    POSITIVE LOGITS
     betweenstory
    1.19
    doi
    1.16
    +#+#
    1.07
     wireType
    1.03
    Personensuche
    1.00
    AnchorTagHelper
    0.98
    HasForeignKey
    0.98
     useEffect
    0.93
     &___
    0.89
    ActionPerformed
    0.89
    Activations Density 0.012%

    No Known Activations