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. 12-GEMMASCOPE-RES-16K
    6. 6362
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to scientific structures, processes, and components

    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
    reactstrap
    -0.85
     nahilalakip
    -0.84
    archiviato
    -0.82
    windowFixed
    -0.82
     AssemblyTitle
    -0.81
    Хьажоргаш
    -0.78
    rungsseite
    -0.78
    xase
    -0.76
    Personendaten
    -0.76
    djangoproject
    -0.76
    POSITIVE LOGITS
     terrorismo
    0.50
    ConstraintMaker
    0.46
    RectangleBorder
    0.43
    ziała
    0.43
     kunci
    0.42
     ahol
    0.41
     ayı
    0.41
     immor
    0.40
    دیگر
    0.40
     koş
    0.40
    Activations Density 1.645%

    No Known Activations