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. 20-GEMMASCOPE-RES-16K
    6. 1098
    Prev
    Next
    INDEX
    Explanations

    corporate and organizational names in relation to their operations and affiliations

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

    New York and Connecticut locations

    np_acts-logits-general · gemini-2.0-flash

    New York and Connecticut locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -1.21
     Lubbock
    -0.75
     Amarillo
    -0.75
    Obrázky
    -0.69
    WebVitals
    -0.67
     Huerta
    -0.66
     Waco
    -0.66
    principalColumn
    -0.65
    Oklahoma
    -0.65
     Cactus
    -0.65
    POSITIVE LOGITS
     NYS
    0.90
     Connecticut
    0.87
     Westchester
    0.84
     Bronx
    0.83
    Connecticut
    0.81
     Schenectady
    0.78
     NY
    0.78
     SUNY
    0.76
     NYC
    0.75
     NYPD
    0.74
    Activations Density 0.747%

    No Known Activations