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. 10328
    Prev
    Next
    INDEX
    Explanations

    negative or denying language in sentences, particularly regarding expectations or requirements

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

    Follows a negation

    np_acts-logits-general · gemini-2.0-flash

    not necessarily

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     rather
    -0.74
    rather
    -0.71
     Somewhat
    -0.69
     partly
    -0.68
     Partly
    -0.67
     Partially
    -0.66
     piuttosto
    -0.65
     bastante
    -0.64
     somewhat
    -0.63
    AsUp
    -0.63
    POSITIVE LOGITS
     necessarily
    1.07
     necessariamente
    1.04
     magically
    0.97
     necesariamente
    0.91
    necessarily
    0.85
     nécessairement
    0.83
     magic
    0.74
     automatically
    0.73
     pana
    0.70
    automatically
    0.68
    Activations Density 0.705%

    No Known Activations