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. 9-GEMMASCOPE-RES-16K
    6. 7891
    Prev
    Next
    INDEX
    Explanations

    information related to project results and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PreferredItem
    -0.58
    EDEFAULT
    -0.58
    KommentareTeilen
    -0.57
    \{\\
    -0.57
    tanian
    -0.54
     ویکی‌پدیا
    -0.52
    addContainerGap
    -0.51
     kasarigan
    -0.50
     AssemblyCompany
    -0.50
     rowspan
    -0.50
    POSITIVE LOGITS
     tests
    0.62
    TargetException
    0.58
     test
    0.52
    يميديا
    0.51
     round
    0.50
    سطس
    0.49
     ходе
    0.49
    Round
    0.47
    testcase
    0.47
     whither
    0.47
    Activations Density 0.851%

    No Known Activations