© 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 - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 13458
    Prev
    Next
    INDEX
    Explanations

    terms and names related to mathematical concepts, studies, and theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ly
    -1.03
    ization
    -0.93
    theless
    -0.91
    lore
    -0.87
    endphp
    -0.87
     Prow
    -0.86
    Gerry
    -0.86
    cbb
    -0.83
    selves
    -0.83
     Poche
    -0.82
    POSITIVE LOGITS
    ing
    1.30
    ة
    0.99
    ladolid
    0.98
    .’
    0.94
    )))
    0.92
    ING
    0.90
     Morris
    0.89
    ’).
    0.87
    AFFIRMED
    0.85
     Dumont
    0.85
    Activations Density 1.843%

    No Known Activations