© 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. 38632
    Prev
    Next
    INDEX
    Explanations

    instances of the word "distinguish" and its variants

    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
    SequentialGroup
    -0.81
     آور
    -0.71
    ⃗
    -0.71
     nadzie
    -0.71
     baisse
    -0.69
     scheda
    -0.69
     Alha
    -0.68
    horabuena
    -0.67
    Pty
    -0.66
     prática
    -0.66
    POSITIVE LOGITS
     distingu
    1.23
     distinguishing
    1.09
     distinguish
    1.09
     distinguishes
    1.07
    inguishing
    1.06
     disting
    1.02
    distingu
    1.01
     distinctions
    0.98
     distingue
    0.98
     differentiate
    0.95
    Activations Density 0.026%

    No Known Activations