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. 1-GEMMASCOPE-RES-16K
    6. 13364
    Prev
    Next
    INDEX
    Explanations

    repetitions of the word "especially" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.94
    XmlAccessType
    -0.75
    xically
    -0.70
    QMetaType
    -0.68
    HasForeignKey
    -0.67
    Rüyada
    -0.66
    rouille
    -0.66
    ificantly
    -0.61
    rrggbb
    -0.61
    cokinetics
    -0.60
    POSITIVE LOGITS
     Even
    0.82
    innerHTML
    0.82
    Even
    0.80
    rungsseite
    0.80
     &[
    0.65
     hình
    0.64
     EVEN
    0.61
    会
    0.59
    ">//
    0.58
     !(
    0.57
    Activations Density 0.252%

    No Known Activations