© 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. 0-GEMMASCOPE-RES-65K
    11. 9235
    Prev
    Next
    INDEX
    Explanations

    references to excellence and phrases related to thinness or war

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dem
    -0.51
     peine
    -0.47
    конец
    -0.46
     encor
    -0.45
    áctica
    -0.45
     namin
    -0.44
    FormBuilder
    -0.44
     Tsu
    -0.44
     sti
    -0.44
     Scha
    -0.43
    POSITIVE LOGITS
    migrationBuilder
    0.84
     oprot
    0.76
     îna
    0.75
    esModule
    0.73
     AssemblyProduct
    0.73
     Sicherung
    0.73
     restored
    0.71
     restoration
    0.70
     dolomite
    0.69
    بوابة
    0.68
    Activations Density 0.039%

    No Known Activations