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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 619
    Prev
    Next
    INDEX
    Explanations

    references to the element Tellurium (Te) and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Izvori
    -0.67
    CreateModel
    -0.64
    Sklici
    -0.62
     Pingback
    -0.61
     ब्रेकडाउन
    -0.61
    getExternal
    -0.61
     ویکی‌پدیا
    -0.60
     Senhora
    -0.60
     Señora
    -0.59
    sizeCache
    -0.58
    POSITIVE LOGITS
     Te
    0.57
     Teas
    0.51
     stesso
    0.47
    Te
    0.46
    +};
    0.44
     stessa
    0.44
     Teg
    0.43
    sterone
    0.41
     mơ
    0.39
     same
    0.39
    Activations Density 0.076%

    No Known Activations