© 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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14065
    Prev
    Next
    INDEX
    Explanations

    references to a specific person or entity named "Ry"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Eloquent
    -0.70
     ISNI
    -0.68
     الدولى
    -0.67
     estekak
    -0.65
    Enllaces
    -0.60
    ectady
    -0.60
    mitas
    -0.57
    +#+#
    -0.56
    saraba
    -0.55
     nakalista
    -0.55
    POSITIVE LOGITS
    Ry
    0.63
     Ry
    0.61
    Responder
    0.58
    IActionResult
    0.52
     connais
    0.50
     ry
    0.49
    Rye
    0.48
    khidmatan
    0.47
    Sizer
    0.47
     amitié
    0.47
    Activations Density 0.137%

    No Known Activations