© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 39503
    Prev
    Next
    INDEX
    Explanations

    coordinating conjunctions that connect clauses or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.94
     disambiguazione
    -0.90
    AccessorTable
    -0.75
    GeoNames
    -0.73
     تضيفلها
    -0.73
     calendriers
    -0.71
    SharedDtor
    -0.67
    rawDesc
    -0.66
    InputTagHelper
    -0.65
    AndEndTag
    -0.65
    POSITIVE LOGITS
     whose
    0.81
    whose
    0.64
     who
    0.63
     Whose
    0.56
     appunto
    0.54
    Whose
    0.53
    %;
    
    0.52
     whom
    0.52
     والذي
    0.50
     cuyo
    0.49
    Activations Density 0.110%

    No Known Activations