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

    Neuronpedia

    APICircuit 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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53006
    Prev
    Next
    INDEX
    Explanations

    the phrase "you know" in various contexts

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

    phrases involving know

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     onStop
    -0.56
    ísimas
    -0.52
    هم
    -0.49
    -<
    -0.49
    _{\
    -0.48
    morris
    -0.48
     Th
    -0.47
    ksamkeit
    -0.46
    Vit
    -0.46
     موجود
    -0.45
    POSITIVE LOGITS
    interopRequire
    0.87
    دانشنامهٔ
    0.77
     AssemblyTitle
    0.73
    EndProject
    0.70
     חיצוניים
    0.68
    ніципа
    0.67
    esModule
    0.67
    ')}}">
    0.66
    HostException
    0.65
     препратки
    0.65
    Activations Density 0.004%

    No Known Activations