© 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. 13629
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific measurements or data attributes

    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
    __*/
    -0.74
    NOPQRST
    -0.61
    +#+#
    -0.59
    GOTREF
    -0.58
     MainAxisSize
    -0.56
     himſelf
    -0.55
     ExecuteAsync
    -0.55
     reafon
    -0.54
    Cyfeiriadau
    -0.52
     Diſ
    -0.52
    POSITIVE LOGITS
    SequentialGroup
    0.52
    mobileqq
    0.51
    UserScript
    0.50
    Negocio
    0.49
     kasarigan
    0.47
    wijs
    0.46
    eap
    0.46
     reserva
    0.45
     BeautifulSoup
    0.45
    wnież
    0.44
    Activations Density 1.180%

    No Known Activations