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. 6-GEMMASCOPE-RES-16K
    6. 12120
    Prev
    Next
    INDEX
    Explanations

    references to judicial canons and their implications for campaign conduct

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -1.26
    ModelAttribute
    -1.11
    
    -1.07
    UnusedPrivate
    -1.05
     дописавши
    -1.04
    ########.
    -1.04
     Numerade
    -1.04
    ніципалі
    -1.02
    addCriterion
    -1.02
     bVar
    -1.01
    POSITIVE LOGITS
    Bbb
    0.74
    n
    0.69
     McCar
    0.68
     capito
    0.67
    ver
    0.66
    ECE
    0.66
     years
    0.65
    рги
    0.65
     “
    0.64
    mis
    0.62
    Activations Density 2.444%

    No Known Activations