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. 1095
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to scientific and technological processes

    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
    GEBURTSDATUM
    -0.97
    expandindo
    -0.67
    rawDesc
    -0.63
    complexContent
    -0.62
    EDEFAULT
    -0.60
    RepeatedField
    -0.59
    InstrumentedTest
    -0.57
    djangoproject
    -0.56
    Adds
    -0.56
    URLException
    -0.55
    POSITIVE LOGITS
     llamada
    0.61
    比如
    0.59
     called
    0.53
     chamada
    0.52
     formats
    0.51
     chamado
    0.50
     namely
    0.50
     geldig
    0.50
     llamado
    0.49
    новид
    0.49
    Activations Density 1.539%

    No Known Activations