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. 847
    Prev
    Next
    INDEX
    Explanations

    references to specific U.S. states and their related information

    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
     EconPapers
    -0.69
    setViewportView
    -0.60
    SerializedName
    -0.54
     ostavi
    -0.54
    NOPQRST
    -0.52
    Autoritní
    -0.49
    wußt
    -0.48
     múl
    -0.48
     root
    -0.48
    Παραπομπές
    -0.47
    POSITIVE LOGITS
     Texas
    1.52
     Illinois
    1.45
     Florida
    1.44
    Texas
    1.41
     Tennessee
    1.38
    Illinois
    1.36
    Florida
    1.35
     Missouri
    1.32
     Wisconsin
    1.30
     Pennsylvania
    1.30
    Activations Density 0.416%

    No Known Activations