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. 0-GEMMASCOPE-RES-16K
    6. 246
    Prev
    Next
    INDEX
    Explanations

    the phrase "hadn't" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Демографія
    -0.63
    Externé
    -0.54
    HMIS
    -0.52
    cemic
    -0.50
    WebElementEntity
    -0.50
     majeur
    -0.49
     acrylique
    -0.49
     fiscale
    -0.49
    braucher
    -0.49
     разве
    -0.49
    POSITIVE LOGITS
     hadn
    2.13
    had
    1.08
     Había
    0.92
    Had
    0.92
     habían
    0.91
     havia
    0.90
    tvguidetime
    0.89
     había
    0.87
     Had
    0.86
     HAD
    0.84
    Activations Density 0.036%

    No Known Activations