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. 16-GEMMASCOPE-RES-16K
    6. 3024
    Prev
    Next
    INDEX
    Explanations

    emotional responses and sentiments expressed towards experiences or events

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

    End of sentences

    np_acts-logits-general · gemini-2.0-flash

    . or comma followed by word

    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
    bigoplus
    -0.55
    Compartir
    -0.54
     prêtres
    -0.53
    はじめに
    -0.52
     Asimismo
    -0.52
     disegno
    -0.51
     prisonniers
    -0.51
     chrétiens
    -0.51
     fièvre
    -0.50
     forbin
    -0.50
    POSITIVE LOGITS
     Great
    0.90
     gotta
    0.89
     still
    0.88
     nice
    0.83
     great
    0.83
     no
    0.82
     very
    0.82
     Very
    0.82
     good
    0.81
     Good
    0.80
    Activations Density 0.313%

    No Known Activations