© 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. 15-GEMMASCOPE-RES-16K
    6. 13604
    Prev
    Next
    INDEX
    Explanations

    specific references to locations and scientific terms, particularly related to Puerto Rico and biology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.93
     Pohl
    -0.85
    rophore
    -0.75
    DotNetBar
    -0.75
     Malone
    -0.74
    Bras
    -0.74
     Fitzgerald
    -0.68
     Bloomfield
    -0.68
     }^{[
    -0.67
     DOCUMENT
    -0.67
    POSITIVE LOGITS
    ;;)
    0.83
     "..\..\
    0.79
    orance
    0.78
     uniti
    0.75
    ?")
    0.75
    ❤❤
    0.73
     }],
    0.72
    )")
    0.72
    .”)
    0.72
    .")
    0.71
    Activations Density 0.567%

    No Known Activations