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. 11-GEMMASCOPE-RES-16K
    6. 1773
    Prev
    Next
    INDEX
    Explanations

    specific mentions of significant events or terms related to specific medical conditions

    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
    RTGC
    -0.57
     Drink
    -0.56
    Drink
    -0.52
    <eos>
    -0.48
    adaptiveStyles
    -0.48
    ibilità
    -0.47
    ldg
    -0.46
    copes
    -0.45
    olate
    -0.45
    jov
    -0.45
    POSITIVE LOGITS
    RenderAtEndOf
    0.87
    зулта
    0.67
    basicConfig
    0.62
     newOwner
    0.61
    makeConstraints
    0.61
    Obrázky
    0.60
     ſec
    0.58
     esternos
    0.57
    存于互联网档案馆
    0.57
    autogui
    0.57
    Activations Density 0.252%

    No Known Activations