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. 22-GEMMASCOPE-RES-16K
    6. 10498
    Prev
    Next
    INDEX
    Explanations

    references to test configurations and processes in a software testing context

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

    Configuration or customization options

    np_acts-logits-general · gemini-2.0-flash

    configure, create, or assign options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    niająca
    -0.72
    ReusableCell
    -0.69
    InstrumentedTest
    -0.67
    ChildScrollView
    -0.67
    windowFixed
    -0.67
    HasAnnotation
    -0.65
     ویکی‌پدی
    -0.63
    Хьажоргаш
    -0.63
    protoimpl
    -0.63
    ThemeOverlay
    -0.62
    POSITIVE LOGITS
     custom
    0.84
     assign
    0.83
     assigned
    0.82
     setup
    0.80
     admin
    0.78
     Custom
    0.77
     Create
    0.77
     configure
    0.76
     configurable
    0.75
     configured
    0.75
    Activations Density 0.548%

    No Known Activations