© 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. 1-GEMMASCOPE-RES-16K
    6. 9917
    Prev
    Next
    INDEX
    Explanations

    instances of the word "reject" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Хьажоргаш
    -0.83
    abestanden
    -0.79
     typelib
    -0.70
    +#+#
    -0.68
     AssemblyProduct
    -0.64
    GeneratedCode
    -0.64
     BrowserRouter
    -0.62
    BrowserRouter
    -0.60
    /**
    -0.59
    ($__
    -0.59
    POSITIVE LOGITS
     reject
    2.63
     rejection
    2.54
     rejected
    2.54
     rejecting
    2.47
     rejects
    2.38
     Reject
    2.37
     Rejection
    2.32
     Rejected
    2.06
    reject
    2.05
    Reject
    2.03
    Activations Density 0.136%

    No Known Activations