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. 21-GEMMASCOPE-RES-16K
    6. 12468
    Prev
    Next
    INDEX
    Explanations

    specific geographic locations and notable venues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     >=",
    -0.77
     defaultstate
    -0.74
    minecraftforge
    -0.66
    
    -0.63
    Lähteet
    -0.56
    Bioaccumulative
    -0.56
    ///</
    -0.56
    Дереккөздер
    -0.55
    三国
    -0.54
    Зноскі
    -0.54
    POSITIVE LOGITS
     NYC
    1.65
     Manhattan
    1.56
    NYC
    1.54
     NY
    1.50
     NYPD
    1.46
    NY
    1.40
    Manhattan
    1.31
     nyc
    1.31
     Bronx
    1.31
     Brooklyn
    1.25
    Activations Density 0.360%

    No Known Activations