© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 38043
    Prev
    Next
    INDEX
    Explanations

    references to identity and mistaken identity

    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
    bias
    -0.52
     fédéral
    -0.51
    bitField
    -0.51
    treat
    -0.51
    PLEMENT
    -0.48
    Bias
    -0.47
    èvement
    -0.47
     quo
    -0.46
    zeciw
    -0.45
    nega
    -0.45
    POSITIVE LOGITS
    cloned
    0.71
     cloned
    0.70
     TextAppearance
    0.63
     impostor
    0.61
     imposter
    0.60
     swapped
    0.59
     imperson
    0.59
    AnchorStyles
    0.58
     GenerationType
    0.58
    withIdentifier
    0.57
    Activations Density 0.211%

    No Known Activations