© 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. 31-GEMMASCOPE-RES-16K
    11. 6408
    Prev
    Next
    INDEX
    Explanations

    cases where there is a contrast or contradiction in statements, often conveyed through the use of "but."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    contrasting phrases introduced by "but" that shift focus or present an alternative perspective.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roskov
    -0.68
    IntoConstraints
    -0.58
    InputBorder
    -0.55
    既
    -0.51
     accordingly
    -0.46
    ensement
    -0.46
     likewise
    -0.45
    antaine
    -0.45
     bezeichneter
    -0.44
    antMatchers
    -0.44
    POSITIVE LOGITS
     vielmehr
    1.17
    むしろ
    0.84
     rather
    0.83
    而是
    0.83
    Rather
    0.81
     raczej
    0.80
     скорее
    0.78
     plutôt
    0.77
     Rather
    0.72
     بلکه
    0.71
    Activations Density 0.348%

    No Known Activations