© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15461
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and equations involving variables

    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
     Dionys
    -0.59
    ponible
    -0.58
     Geraadpleegd
    -0.58
    WebElementEntity
    -0.57
     interak
    -0.56
     Doubleday
    -0.56
     sèche
    -0.56
     AspNetCore
    -0.55
    Gambas
    -0.55
     grecque
    -0.54
    POSITIVE LOGITS
    LookAnd
    0.55
     tkinter
    0.54
     must
    0.53
    requestCode
    0.52
    Sklici
    0.52
     createState
    0.52
     useDispatch
    0.51
    CharField
    0.49
    Referencies
    0.48
    AndEndTag
    0.47
    Activations Density 1.431%

    No Known Activations