© 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-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 3157
    Prev
    Next
    INDEX
    Explanations

    references to emphasis or importance in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    moveToFirst
    -0.69
    Produzione
    -0.63
     Barker
    -0.61
    őtt
    -0.60
    AndEndTag
    -0.59
    Cuc
    -0.59
    <?
    -0.58
    loem
    -0.58
     numerus
    -0.56
    ContentLoaded
    -0.56
    POSITIVE LOGITS
     emphas
    1.48
     emphasise
    1.46
     emphasis
    1.46
     Emphasis
    1.41
     emphasised
    1.37
     emphasizing
    1.32
     emphasize
    1.30
     emphasizes
    1.28
     highlight
    1.26
     emphasized
    1.24
    Activations Density 0.056%

    No Known Activations