© 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. 10557
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparisons or distinctions between options or ideas

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

    the word "former" when it appears in comparative contexts contrasting two options or alternatives.

    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
    StoryboardSegue
    -0.52
    RenderAtEndOf
    -0.51
    EndProject
    -0.49
     pleaſure
    -0.47
     blockSize
    -0.47
     faſt
    -0.47
    sole
    -0.46
    下载附件
    -0.46
    ьажоргаш
    -0.46
     carc
    -0.44
    POSITIVE LOGITS
     latter
    3.16
    后者
    2.41
    latter
    2.05
     letz
    1.55
     Latter
    1.40
     éste
    1.31
     éstos
    1.28
     senare
    1.27
     former
    1.20
     ésta
    1.16
    Activations Density 0.680%

    No Known Activations