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-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 8056
    Prev
    Next
    INDEX
    Explanations

    terms related to data handling and logging processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -1.21
    NameInMap
    -1.04
    SourceChecksum
    -0.93
    +#+#
    -0.92
    IsMutable
    -0.92
     Himo
    -0.92
     سكانية
    -0.88
     كومونز
    -0.87
    ьаж
    -0.87
    RegistryLite
    -0.86
    POSITIVE LOGITS
    reportWebVitals
    0.45
    apatos
    0.41
    ða
    0.37
     surla
    0.35
     >>=
    0.35
    ตร
    0.34
    ijin
    0.34
     pint
    0.34
     délé
    0.34
    Razor
    0.33
    Activations Density 0.851%

    No Known Activations