Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 4674
    Prev
    Next
    INDEX
    Explanations

    instances of realization or awareness in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    udsman
    -0.65
     ویکی‌پدیای
    -0.63
     Bag
    -0.62
    mun
    -0.60
    ffeine
    -0.60
    〉
    -0.59
     dys
    -0.59
    баты
    -0.59
    Pozdrawiam
    -0.59
     cellpadding
    -0.58
    POSITIVE LOGITS
     realises
    1.34
     realise
    1.32
     realizes
    1.31
     realising
    1.31
     realize
    1.29
     realizing
    1.28
     realisation
    1.28
     realization
    1.23
     realised
    1.16
     realized
    1.14
    Activations Density 0.030%

    No Known Activations