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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 14341
    Prev
    Next
    INDEX
    Explanations

    instances of the word "nice" 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 @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     getRule
    -0.61
    DebuggerNonUser
    -0.54
     drept
    -0.53
    hingga
    -0.53
     bodem
    -0.52
    Kariera
    -0.52
    Yen
    -0.49
    signIn
    -0.49
    ásra
    -0.48
    eraard
    -0.48
    POSITIVE LOGITS
     smelling
    0.81
     nice
    0.81
     neat
    0.79
    ties
    0.79
     little
    0.77
    NICE
    0.74
     tidy
    0.72
     clean
    0.70
    nice
    0.70
     lookin
    0.69
    Activations Density 0.062%

    No Known Activations