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. 22-GEMMASCOPE-RES-16K
    6. 10507
    Prev
    Next
    INDEX
    Explanations

    references to specific locations, particularly towns and geographical areas

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

    Locations in Florida and California

    np_acts-logits-general · gemini-2.0-flash

    cities in florida and california

    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
     Emmer
    -0.56
    LookAnd
    -0.48
    ñones
    -0.48
     Ide
    -0.47
    tableFuture
    -0.47
    __*/
    -0.47
     Dorchester
    -0.47
    findpost
    -0.47
    giers
    -0.47
     typename
    -0.45
    POSITIVE LOGITS
     Orange
    1.41
    Orange
    1.33
     ORANGE
    1.20
    ORANGE
    1.16
     orange
    1.00
    orange
    0.99
     Oranges
    0.97
     Orlando
    0.96
     Irvine
    0.95
     naranja
    0.95
    Activations Density 0.151%

    No Known Activations