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. 7-GEMMASCOPE-RES-16K
    6. 6410
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "goods" and related terms, indicating a focus on items or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.86
    دانشنامهٔ
    -0.82
     Meksiku
    -0.76
     tramonto
    -0.73
    ︎
    -0.73
    PreAuthorize
    -0.71
     encou
    -0.69
    fromCharCode
    -0.69
    execSQL
    -0.67
    pidou
    -0.67
    POSITIVE LOGITS
     Goods
    1.56
     goods
    1.55
    Goods
    1.31
     GOODS
    1.27
    goods
    1.25
     goederen
    0.92
     Commodities
    0.85
    货
    0.85
     Waren
    0.81
     commodity
    0.80
    Activations Density 0.088%

    No Known Activations