© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 5-GEMMASCOPE-RES-16K
    11. 7611
    Prev
    Next
    INDEX
    Explanations

    conjunctions that indicate connections and comparisons in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     R
    -0.57
     I
    -0.56
    <eos>
    -0.55
     information
    -0.53
     -
    -0.52
     i
    -0.52
     N
    -0.52
     two
    -0.52
    ↵↵
    -0.52
     Ex
    -0.51
    POSITIVE LOGITS
    存于互联网档案馆
    0.89
     AssemblyCulture
    0.87
    ագրություններ
    0.81
     Мексичка
    0.81
    tvguidetime
    0.79
     незавершена
    0.78
    ształ
    0.77
    AnchorStyles
    0.75
     виправивши
    0.73
     كومونز
    0.72
    Activations Density 0.322%

    No Known Activations