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. 9-GEMMASCOPE-RES-16K
    6. 7985
    Prev
    Next
    INDEX
    Explanations

    phrases related to integration and consolidation of various elements into a unified system

    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
    InjectAttribute
    -0.97
    httphttps
    -0.67
    CppMethod
    -0.64
    HtmlAttribute
    -0.62
    PreExecute
    -0.60
    LookAnd
    -0.59
     ویکی‌پدی
    -0.56
    ViewFeatures
    -0.56
     AssemblyCompany
    -0.56
     localObject
    -0.54
    POSITIVE LOGITS
     unified
    0.93
    unified
    0.92
     unifying
    0.82
     consolidated
    0.77
     unify
    0.75
    統合
    0.74
     unification
    0.74
    Unified
    0.74
    统一
    0.74
     consolidating
    0.72
    Activations Density 0.406%

    No Known Activations