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. 2-GEMMASCOPE-RES-16K
    6. 3728
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific names related to individuals and entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sucesor
    -1.06
     snippetHide
    -1.06
    Hauptartikel
    -1.03
    awtextra
    -1.03
    ГЛА
    -0.99
     }}"></
    -0.98
     autorytatywna
    -0.94
    --}}
    -0.93
    "]).
    -0.91
     beginnetje
    -0.90
    POSITIVE LOGITS
     Lubbock
    0.77
     Greenwich
    0.73
     Valenzuela
    0.70
     harina
    0.68
    évaluateur
    0.66
     vocale
    0.65
     témoin
    0.64
     Alvin
    0.63
     Dhabi
    0.62
     Bop
    0.61
    Activations Density 9.226%

    No Known Activations