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. 19-GEMMASCOPE-RES-16K
    6. 3586
    Prev
    Next
    INDEX
    Explanations

    articles and conjunctions in German language texts

    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
     ſche
    -0.75
     typelib
    -0.71
     pleaſure
    -0.70
    tvguidetime
    -0.70
     оригіналу
    -0.70
     Viceroy
    -0.70
     purpoſe
    -0.69
     betweenstory
    -0.69
     auffi
    -0.67
     colic
    -0.66
    POSITIVE LOGITS
    dani
    0.66
     hier
    0.57
    URY
    0.54
     här
    0.54
    OMON
    0.54
     ici
    0.54
     Sa
    0.53
    mán
    0.52
     ini
    0.52
     Here
    0.51
    Activations Density 0.019%

    No Known Activations