© 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 - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 9537
    Prev
    Next
    INDEX
    Explanations

    actions and conditions related to permission or assessment

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    expandindo
    -1.19
     itself
    -0.85
    itself
    -0.83
    contentLoaded
    -0.83
     насељу
    -0.82
     Itself
    -0.81
     дописавши
    -0.81
    bootstrapcdn
    -0.79
    mybatisplus
    -0.76
     للمعارف
    -0.75
    POSITIVE LOGITS
     are
    0.86
     themselves
    0.81
     ARE
    0.69
     were
    0.67
     aren
    0.67
     their
    0.61
    were
    0.61
    Are
    0.60
     weren
    0.60
    themselves
    0.59
    Activations Density 0.603%

    No Known Activations