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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 30318
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and phrases related to web security and data integrity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    substitute, fake, replace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.57
     VizieR
    -0.49
     SLR
    -0.48
     участь
    -0.48
    ául
    -0.47
     démoc
    -0.47
    toISOString
    -0.47
    abetes
    -0.47
    ulipas
    -0.46
    ništ
    -0.45
    POSITIVE LOGITS
     substitute
    0.84
    tdessen
    0.79
     fake
    0.79
     вместо
    0.78
     substitutes
    0.77
     palsu
    0.76
     instead
    0.75
    fake
    0.74
     substituted
    0.74
     falschen
    0.73
    Activations Density 0.454%

    No Known Activations