© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 12859
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate offers or proposals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.76
    ChromeDriver
    -0.72
     <=",
    -0.71
    IUrlHelper
    -0.70
    Vidite
    -0.70
     Initialized
    -0.69
    GeneratedMessage
    -0.66
     StatelessWidget
    -0.66
     accompan
    -0.66
    Bibliograf
    -0.64
    POSITIVE LOGITS
     offered
    1.57
     offer
    1.46
     offers
    1.44
    offered
    1.39
     Offered
    1.37
    Offered
    1.37
     offering
    1.33
    offers
    1.30
     OFFER
    1.22
     Offers
    1.18
    Activations Density 0.134%

    No Known Activations