Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 10222
    Prev
    Next
    INDEX
    Explanations

    terms associated with empirical research and experimental conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.60
    PullParser
    -0.56
    rrggbb
    -0.52
     cellpadding
    -0.52
    XmlAccessorType
    -0.51
     betweenstory
    -0.51
    bonucleic
    -0.50
     prieten
    -0.50
     jsPsych
    -0.50
    >(&
    -0.50
    POSITIVE LOGITS
     reality
    0.91
     realities
    0.82
    reality
    0.81
     Reality
    0.80
     réalité
    0.78
     actuality
    0.77
    Reality
    0.75
     realidade
    0.66
    vivo
    0.66
    实际
    0.66
    Activations Density 0.638%

    No Known Activations