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. 18-GEMMASCOPE-RES-16K
    6. 421
    Prev
    Next
    INDEX
    Explanations

    any references to layout elements and their properties in the code

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

    UI "layout" properties

    np_acts-logits-general · gemini-2.0-flash

    layout

    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
     Mero
    -0.68
    gebnisse
    -0.68
    Cerv
    -0.66
     vụ
    -0.61
    ylabel
    -0.58
    phins
    -0.58
    brands
    -0.58
     getNumber
    -0.57
    hesus
    -0.57
    protoimpl
    -0.56
    POSITIVE LOGITS
     getLayout
    1.05
     layouts
    0.97
    BoxLayout
    0.93
     LAYOUT
    0.82
     Layout
    0.82
     layout
    0.81
    LAYOUT
    0.79
    Layouts
    0.78
    layouts
    0.74
    layoutControl
    0.73
    Activations Density 0.161%

    No Known Activations