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-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 2051
    Prev
    Next
    INDEX
    Explanations

    references to individuals and groups within specified contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 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
    MigrationBuilder
    -0.73
    rungsseite
    -0.69
    ChromeDriver
    -0.67
    AndEndTag
    -0.67
     ExecuteAsync
    -0.61
    ConstraintMaker
    -0.61
    windowFixed
    -0.59
    leby
    -0.59
     AssemblyCompany
    -0.56
    Tembelea
    -0.55
    POSITIVE LOGITS
    之一
    0.41
     أحد
    0.35
     egyik
    0.34
     salah
    0.30
    ABAJO
    0.29
     إحدى
    0.29
    ServiceException
    0.28
    InBytes
    0.28
    際には
    0.27
    fgets
    0.27
    Activations Density 0.607%

    No Known Activations