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. 16-GEMMASCOPE-RES-16K
    6. 8907
    Prev
    Next
    INDEX
    Explanations

    negations and contrasting ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows a negative statement

    np_acts-logits-general · gemini-2.0-flash

    no, nope, nein, 違います

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.80
     myſelf
    -0.77
     itſelf
    -0.76
     Monfieur
    -0.72
    SharedDtor
    -0.68
     Efq
    -0.65
     $_"
    -0.64
     Cicero
    -0.62
    cerely
    -0.61
     varandra
    -0.61
    POSITIVE LOGITS
     Nope
    0.80
    Nope
    0.74
     nope
    0.71
     here
    0.63
     Instead
    0.59
    違います
    0.59
    nope
    0.55
    Instead
    0.54
     nein
    0.53
    而是
    0.50
    Activations Density 0.206%

    No Known Activations