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. 12-GEMMASCOPE-RES-16K
    6. 5413
    Prev
    Next
    INDEX
    Explanations

    specific punctuation and sentence-ending structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     amelyek
    -0.53
    stoj
    -0.46
     mennes
    -0.45
    ires
    -0.45
     GenerationType
    -0.44
    ">(</
    -0.44
    mans
    -0.44
    Enciclopedia
    -0.43
    ,</
    -0.43
    illan
    -0.42
    POSITIVE LOGITS
     препратки
    0.81
    styleType
    0.72
    :+:
    0.70
    GEBURTSDATUM
    0.65
    sizeCache
    0.64
     referrerpolicy
    0.63
    EDEFAULT
    0.63
     Lightboxes
    0.63
     onCreateView
    0.62
     WaitForSeconds
    0.61
    Activations Density 0.606%

    No Known Activations