Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 15602
    Prev
    Next
    INDEX
    Explanations

    technical specifications and instructions related to layout and orientation in programming

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

    Orientation or alignment of objects

    np_acts-logits-general · gemini-2.0-flash

    spatial orientation and direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.80
     يتيمه
    -0.78
    \{\\
    -0.78
    ChildScrollView
    -0.72
    CloseOperation
    -0.67
    Viited
    -0.67
     betweenstory
    -0.63
     EconPapers
    -0.63
     estimés
    -0.61
    resz
    -0.61
    POSITIVE LOGITS
     perpendicular
    1.24
     sideways
    1.19
     vertical
    1.11
     vertically
    1.08
     horizontally
    1.08
     horizontal
    1.03
     facing
    1.01
     upright
    0.96
    vertical
    0.93
     parallel
    0.90
    Activations Density 0.529%

    No Known Activations