Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 7347
    Prev
    Next
    INDEX
    Explanations

    references to salads and salad-related dishes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebVitals
    -0.79
     onAnimation
    -0.77
    /**
    -0.77
    ]")]
    -0.73
     Dyke
    -0.73
    Xaml
    -0.71
     HET
    -0.70
    XCT
    -0.70
    sud
    -0.70
    octanol
    -0.69
    POSITIVE LOGITS
     Sal
    1.33
     Salad
    1.30
    Sal
    1.27
    Salad
    1.27
     salad
    1.24
     salads
    1.22
     SAL
    1.16
    sal
    1.10
     Salter
    1.09
     sal
    1.09
    Activations Density 0.331%

    No Known Activations