Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-GEMMASCOPE-RES-16K
    6. 11135
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical procedures, regulations, and formal documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -0.87
    性和
    -0.74
    ագրություններ
    -0.60
    XmlAccessType
    -0.58
    Життєпис
    -0.57
     however
    -0.56
     EconPapers
    -0.55
     infatti
    -0.55
    UnitTesting
    -0.55
     or
    -0.54
    POSITIVE LOGITS
     nakalista
    0.73
    hyrchwyd
    0.71
    ướ
    0.63
    abestanden
    0.62
     ostavi
    0.57
     thereof
    0.56
    gration
    0.55
    อื่น
    0.55
     CanadaChoose
    0.55
    ernalia
    0.55
    Activations Density 6.392%

    No Known Activations