© 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. 0-GEMMASCOPE-RES-65K
    6. 9801
    Prev
    Next
    INDEX
    Explanations

    phrases related to authenticity or reality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.68
     culturelles
    -0.59
     pyruvate
    -0.55
    ItemBackground
    -0.53
     dépens
    -0.53
     Hogarth
    -0.52
     stijl
    -0.52
     volontaire
    -0.52
     seigneur
    -0.51
     toiminta
    -0.51
    POSITIVE LOGITS
    تقاوى
    1.16
     '\\;'
    0.78
    '),
    
    0.75
    parsedMessage
    0.74
     kaarangay
    0.74
     Signalez
    0.73
    ]='\
    0.73
    ,$_
    0.72
    journals
    0.72
    الدراسه
    0.72
    Activations Density 0.086%

    No Known Activations