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. 12896
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with political alliances and conflicts

    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
    artney
    -0.51
    Britannique
    -0.48
     veuillez
    -0.48
     Buon
    -0.48
    ServiceTest
    -0.48
     spécialisé
    -0.45
     compéti
    -0.44
     competition
    -0.44
    quiry
    -0.44
     réalis
    -0.43
    POSITIVE LOGITS
    ReusableCell
    0.76
     ProtoMessage
    0.70
     allies
    0.69
    الإنجليزية
    0.68
    adpleegd
    0.66
    IBarButtonItem
    0.65
     protoimpl
    0.63
    parsedMessage
    0.63
    ConverterFactory
    0.61
     خارجية
    0.61
    Activations Density 0.561%

    No Known Activations