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. 9095
    Prev
    Next
    INDEX
    Explanations

    terms related to charters and the concept of chartered entities

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

    "Char" or "Charter" appearing in text

    np_acts-logits-general · gemini-2.0-flash

    char-, chart- words

    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
    ropods
    -0.69
    LikeLike
    -0.67
     Bina
    -0.67
    DDI
    -0.64
    ieteur
    -0.62
    Kne
    -0.62
    APORE
    -0.62
    Enllaces
    -0.62
    vénients
    -0.62
    📁
    -0.62
    POSITIVE LOGITS
     CHAR
    1.07
     Char
    1.04
    CHAR
    1.00
    Char
    0.96
     Charter
    0.89
     charts
    0.87
     chars
    0.87
     char
    0.85
     Chart
    0.82
     Charts
    0.81
    Activations Density 0.257%

    No Known Activations