© 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. 15-GEMMASCOPE-RES-16K
    11. 1234
    Prev
    Next
    INDEX
    Explanations

    sequence of numerical references or citations in academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SBATCH
    -0.84
     eccell
    -0.65
    PerformLayout
    -0.63
     Efq
    -0.61
     lunghi
    -0.60
    下载附件
    -0.60
    +#+
    -0.59
     fær
    -0.57
    řev
    -0.56
    maka
    -0.56
    POSITIVE LOGITS
     encar
    0.51
     Roskov
    0.50
     jsPsych
    0.50
    发表于
    0.49
    ster
    0.47
     Report
    0.47
    ране
    0.47
    cibles
    0.46
    bitkan
    0.46
    fiés
    0.45
    Activations Density 0.141%

    No Known Activations