© 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 - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 57658
    Prev
    Next
    INDEX
    Explanations

    instances of the beginning of sentences or structured elements in a document

    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
      
    -0.79
     
    -0.74
    NETT
    -0.74
    HasColumnName
    -0.68
    lical
    -0.67
    angdong
    -0.67
    いた
    -0.66
     Hals
    -0.65
    Enfant
    -0.64
    <eos>
    -0.63
    POSITIVE LOGITS
     Hore
    1.51
     Tare
    1.39
     ORE
    1.36
     Sare
    1.33
     Nore
    1.30
     Ure
    1.30
     Kure
    1.27
     Nare
    1.26
     Vire
    1.25
     Mire
    1.24
    Activations Density 0.063%

    No Known Activations