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. 5-GEMMASCOPE-RES-16K
    6. 3667
    Prev
    Next
    INDEX
    Explanations

    the beginning of new sections or significant breaks in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.51
    дь
    -0.46
     combined
    -0.44
     select
    -0.43
    放題
    -0.43
     bi
    -0.42
    ш
    -0.42
     نمایید
    -0.42
     
    -0.41
     resulting
    -0.41
    POSITIVE LOGITS
     '\\;'
    1.15
    AndEndTag
    1.04
    XmlAccessType
    0.99
     Italijanski
    0.98
    RenderAtEndOf
    0.96
    Rüyada
    0.96
    titleMargin
    0.88
     Италијани
    0.80
    Hentet
    0.77
    transQ
    0.77
    Activations Density 0.423%

    No Known Activations