© 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. 11008
    Prev
    Next
    INDEX
    Explanations

    HTML unordered list elements and their attributes

    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
     Azz
    -0.89
    FieldBuilder
    -0.88
     Bridgewater
    -0.87
    ChildScrollView
    -0.85
     McKee
    -0.84
    WireFormatLite
    -0.81
    CDCl
    -0.78
    تقاوى
    -0.78
     Pickett
    -0.78
     Garnier
    -0.76
    POSITIVE LOGITS
     Scully
    0.70
    elems
    0.69
     Vay
    0.69
    ListComponent
    0.69
     Serp
    0.68
     CommonModule
    0.67
     Edmunds
    0.66
     elems
    0.66
     Rowan
    0.65
     helst
    0.64
    Activations Density 0.913%

    No Known Activations