© 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-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 2081
    Prev
    Next
    INDEX
    Explanations

    occurrences of the conjunction "and" or similar conjunctions in complex contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     FetchType
    -0.53
    adaptiveStyles
    -0.52
     poem
    -0.50
     témoig
    -0.50
    IVEREF
    -0.49
     Terraria
    -0.49
     jsPsych
    -0.47
    oa̍t
    -0.46
    tagext
    -0.44
     vnto
    -0.44
    POSITIVE LOGITS
     whereas
    0.73
    而
    0.65
     During
    0.64
     而
    0.60
     during
    0.59
    static
    0.59
    During
    0.59
     DURING
    0.59
    whereas
    0.58
    Sedangkan
    0.57
    Activations Density 0.356%

    No Known Activations