© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 515
    Prev
    Next
    INDEX
    Explanations

    programming elements related to graphical user interface (GUI) components and their properties

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

    Height and width related calculations

    np_acts-logits-general · gemini-2.0-flash

    size and dimensions

    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
    Einzelnachweise
    -0.48
     on
    -0.46
    addGroup
    -0.44
     Sche
    -0.43
     J
    -0.42
    str
    -0.42
    addCriterion
    -0.42
     δε
    -0.42
    ijo
    -0.41
     unter
    -0.41
    POSITIVE LOGITS
    PreferredItem
    1.23
     size
    1.13
    sizeCache
    1.11
    SizeF
    1.00
     height
    1.00
    windowFixed
    0.99
     width
    0.98
     length
    0.95
    ViewFeatures
    0.95
    size
    0.95
    Activations Density 0.140%

    No Known Activations