© 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. 2602
    Prev
    Next
    INDEX
    Explanations

    numerical values or references associated with statistics or reports

    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
    ellees
    -0.81
    Jereo
    -0.78
     ostavi
    -0.67
     חיצוניים
    -0.67
    %")
    -0.65
    Билгалдахарш
    -0.64
    Viited
    -0.63
    Становништво
    -0.62
     })}
    -0.62
     GoogleFonts
    -0.62
    POSITIVE LOGITS
     year
    0.78
    年
    0.67
     année
    0.66
     yılı
    0.64
    year
    0.62
     summer
    0.61
     año
    0.59
     edition
    0.59
     年
    0.59
     season
    0.59
    Activations Density 0.550%

    No Known Activations