© 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. 2-GEMMASCOPE-RES-16K
    11. 6966
    Prev
    Next
    INDEX
    Explanations

    notations and symbols related to graphs and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ClientSize
    -0.73
    #
    -0.65
     Архиви
    -0.65
     Arxivat
    -0.64
    ynchronously
    -0.62
     ivelany
    -0.61
    клопе
    -0.58
    dropna
    -0.58
     Wiesbaden
    -0.58
    CodeDom
    -0.57
    POSITIVE LOGITS
    G
    0.93
    ResumeLayout
    0.58
    nanoTime
    0.54
     mål
    0.53
    المناصب
    0.53
    Hozzáférés
    0.51
    pyplot
    0.50
    endwhile
    0.49
    GED
    0.49
    Gn
    0.47
    Activations Density 0.180%

    No Known Activations