© 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. 11-GEMMASCOPE-RES-16K
    11. 6488
    Prev
    Next
    INDEX
    Explanations

    structured mathematical formulas or references to equations in scientific contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IContainer
    -0.72
     EconPapers
    -0.72
    ########.
    -0.68
     
    -0.66
     referenties
    -0.64
    
    -0.63
     surla
    -0.63
     Roskov
    -0.62
    ⓧ
    -0.62
    ftagPool
    -0.59
    POSITIVE LOGITS
     amarillas
    0.57
    脚注の使い方
    0.52
     blancas
    0.52
    ửa
    0.49
    MigrationBuilder
    0.48
     sillä
    0.47
     ennen
    0.47
     puissiez
    0.46
     sekunder
    0.46
    genstein
    0.46
    Activations Density 0.051%

    No Known Activations