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. 17-GEMMASCOPE-RES-16K
    6. 6012
    Prev
    Next
    INDEX
    Explanations

    attributes related to business management and e-commerce resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Atsauces
    -0.64
    ISupport
    -0.61
     препратки
    -0.60
    PerformLayout
    -0.60
    InjectAttribute
    -0.56
    HORE
    -0.53
     propOrder
    -0.53
    mybatisplus
    -0.52
     ddelweddau
    -0.52
    だからこそ
    -0.50
    POSITIVE LOGITS
     bagus
    0.78
    excellent
    0.76
     excellent
    0.74
     IIRC
    0.74
     http
    0.70
     iirc
    0.69
    おすすめです
    0.67
    erdings
    0.65
     bastante
    0.62
    不錯
    0.60
    Activations Density 0.335%

    No Known Activations