© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 8286
    Prev
    Next
    INDEX
    Explanations

    specific locations and entities, particularly in Florida

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Florida locations and legal procedures

    np_acts-logits-general · gemini-2.0-flash

    Florida cities and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.85
    DeleteBehavior
    -0.79
    Vidite
    -0.67
    MemoryWarning
    -0.66
    GeneratedCode
    -0.66
    contentLoaded
    -0.64
    Билгалдахарш
    -0.62
    PhysRev
    -0.61
     Numerade
    -0.61
    localctx
    -0.57
    POSITIVE LOGITS
     Jacksonville
    0.67
    Jacksonville
    0.56
    atka
    0.55
    Jax
    0.53
     Ponte
    0.49
     Jaguars
    0.49
    jax
    0.48
     прі
    0.48
     Ortega
    0.48
     UNF
    0.47
    Activations Density 0.131%

    No Known Activations