© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 9758
    Prev
    Next
    INDEX
    Explanations

    references to regularity and conventionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "regular"

    np_acts-logits-general · gemini-2.0-flash

    regular, ordinary, normal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.92
     الحره
    -0.79
    AccessorTable
    -0.78
     initComponents
    -0.76
     CreateTagHelper
    -0.73
    IntoConstraints
    -0.73
    enumii
    -0.72
     AssemblyTitle
    -0.72
     Autorizaciones
    -0.69
    HtmlAttribute
    -0.69
    POSITIVE LOGITS
     ordinary
    0.93
     ordinaire
    0.86
     normal
    0.83
     Ordinary
    0.82
     ordinaires
    0.81
    Ordinary
    0.75
     regular
    0.74
     Normal
    0.74
    REGULAR
    0.71
     Regular
    0.69
    Activations Density 0.154%

    No Known Activations