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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 4780
    Prev
    Next
    INDEX
    Explanations

    HTML and JavaScript elements and attributes related to web page structure and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Приступљено
    -0.48
    StringCopy
    -0.47
    ждународ
    -0.47
     mouths
    -0.45
    aites
    -0.45
    曖昧さ回避
    -0.44
    untur
    -0.43
     дописавши
    -0.43
    춰
    -0.42
     dots
    -0.42
    POSITIVE LOGITS
    RenderAtEndOf
    0.72
    IsContent
    0.68
     sidebar
    0.64
    FormTagHelper
    0.61
    ValueStyle
    0.58
     Bread
    0.57
    XmlAccessorType
    0.57
     Content
    0.56
    content
    0.56
     Body
    0.56
    Activations Density 0.165%

    No Known Activations