© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 12763
    Prev
    Next
    INDEX
    Explanations

    relationships and inequalities in mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.57
     useContext
    -0.51
     kesk
    -0.51
    <bos>
    -0.51
    ragamo
    -0.49
    tdessen
    -0.49
    tyfik
    -0.48
     pylori
    -0.48
     nephe
    -0.48
    mlung
    -0.47
    POSITIVE LOGITS
    ารถ
    0.88
    لينكات
    0.85
    تقاوى
    0.82
    Архівовано
    0.81
    hyrchwyd
    0.80
     defaultstate
    0.77
     برانيه
    0.77
    stackrel
    0.75
    Portale
    0.72
    verwijspagina
    0.71
    Activations Density 1.015%

    No Known Activations