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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 2081
    Prev
    Next
    INDEX
    Explanations

    periods and punctuation that signify the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    İstinadlar
    -0.73
    Démographie
    -0.66
    AccessorTable
    -0.64
    原始内容存档于
    -0.59
     typelib
    -0.59
    Достоинства
    -0.57
     ComVisible
    -0.56
    TestTools
    -0.56
    SpringBootTest
    -0.55
    EndProject
    -0.54
    POSITIVE LOGITS
     âgées
    0.62
     connues
    0.50
     définiti
    0.50
     NSCoder
    0.49
     mourut
    0.48
    gatsby
    0.48
    WEBPACK
    0.47
    ulmuş
    0.46
     nacer
    0.46
     виправивши
    0.46
    Activations Density 0.437%

    No Known Activations