© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4908
    Prev
    Next
    INDEX
    Explanations

    numerical data and percentages related to studies and statistics

    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
     ModelExpression
    -0.82
     ujednoznacz
    -0.82
    tvguidetime
    -0.82
    findpost
    -0.79
     NSCoder
    -0.79
     resourceCulture
    -0.78
     defaultstate
    -0.78
    
    -0.77
     المعيارى
    -0.73
    withIdentifier
    -0.71
    POSITIVE LOGITS
     percentage
    0.64
     happy
    0.57
     percent
    0.56
    占比
    0.55
     fraction
    0.55
    percent
    0.53
     feliz
    0.53
    Percent
    0.53
    Percentage
    0.52
    happy
    0.52
    Activations Density 0.304%

    No Known Activations