© 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. 11-GEMMASCOPE-RES-16K
    11. 13577
    Prev
    Next
    INDEX
    Explanations

    terms related to electrical and computational properties in the context of technology and engineering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessType
    -0.55
    orry
    -0.50
     Wiktionnaire
    -0.48
    Diweddarwch
    -0.48
    ysen
    -0.48
    InputTagHelper
    -0.47
    izard
    -0.46
    Rohy
    -0.45
    WebServlet
    -0.45
    干
    -0.44
    POSITIVE LOGITS
     كومونز
    0.64
     referrerpolicy
    0.62
     Infórmanos
    0.59
    oneofs
    0.58
     Efq
    0.57
    GOTREF
    0.56
     myſelf
    0.56
    पया
    0.55
     "..\..\..\
    0.54
     handelt
    0.54
    Activations Density 0.518%

    No Known Activations