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. 16-GEMMASCOPE-RES-16K
    6. 1430
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts related to geometry and line equations

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

    Lines and equations

    np_acts-logits-general · gemini-2.0-flash

    line, plane, equation, geometry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interopRequire
    -0.55
    Personensuche
    -0.51
    quence
    -0.49
     size
    -0.48
     oprot
    -0.47
    vestres
    -0.47
     substitution
    -0.46
     ControllerBase
    -0.46
     micro
    -0.46
    GetKeyDown
    -0.46
    POSITIVE LOGITS
    principalTable
    0.71
     bancaire
    0.57
    slope
    0.56
    таратура
    0.55
    weiler
    0.55
    Vorlage
    0.54
    Paint
    0.53
    ipers
    0.52
     invités
    0.52
    warted
    0.52
    Activations Density 0.679%

    No Known Activations