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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-GEMMASCOPE-RES-16K
    6. 6085
    Prev
    Next
    INDEX
    Explanations

    chemical compounds related to synthetic processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kal
    -0.72
    __*/
    -0.66
    Kal
    -0.66
    Tikang
    -0.62
    goog
    -0.57
     positivas
    -0.53
     estekak
    -0.53
     Meksiku
    -0.53
     ग्राहकों
    -0.52
     ©️
    -0.52
    POSITIVE LOGITS
    ide
    2.16
    IDE
    1.49
    ides
    1.10
     ide
    1.00
    IDES
    0.94
    Ide
    0.88
     Ide
    0.80
     IDE
    0.76
    iding
    0.73
    idet
    0.73
    Activations Density 0.166%

    No Known Activations