© 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. 1842
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases that highlight the features and benefits of products or concepts

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

    words that appear frequently in product descriptions and promotional content, particularly nouns and adjectives used to describe items being sold or recommended.

    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
     OFDb
    -0.44
    isContained
    -0.33
    gelöst
    -0.33
     siquiera
    -0.32
    utilisons
    -0.32
    四年
    -0.31
    principalColumn
    -0.31
    EReference
    -0.31
    keyColumn
    -0.31
    日閲覧
    -0.30
    POSITIVE LOGITS
     perfect
    2.89
     ideal
    2.81
    perfect
    2.55
    ideal
    2.41
    Perfect
    2.30
    Ideal
    2.28
     ideale
    2.27
     Perfect
    2.25
     Ideal
    2.22
     PERFECT
    2.20
    Activations Density 0.513%

    No Known Activations