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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19-GEMMASCOPE-RES-16K
    6. 2034
    Prev
    Next
    INDEX
    Explanations

    financial terms and concepts related to credit and loan opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Toward
    -0.61
    toward
    -0.51
    Toward
    -0.51
    leqq
    -0.49
    hezza
    -0.49
    stacles
    -0.46
     menudo
    -0.46
    rogly
    -0.45
    Hometown
    -0.45
    গু
    -0.45
    POSITIVE LOGITS
     availed
    0.85
     hence
    0.80
     severally
    0.77
     adverts
    0.76
     Programmes
    0.75
     commonest
    0.75
     learnt
    0.73
     spoilt
    0.71
     advert
    0.70
     envisaged
    0.69
    Activations Density 0.298%

    No Known Activations