© 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. 17-GEMMASCOPE-RES-16K
    11. 7018
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols related to calculus and statistical functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quitt
    -0.40
     cores
    -0.39
    HomeAsUpEnabled
    -0.39
    nisch
    -0.37
     plong
    -0.37
    úr
    -0.36
     longue
    -0.36
     خالی
    -0.36
     dedo
    -0.36
    どちら
    -0.36
    POSITIVE LOGITS
    :✨
    1.02
     Réponses
    0.88
    postsleuth
    0.83
     lenker
    0.80
    országban
    0.79
    ImageContext
    0.78
    aarrggbb
    0.76
    kháu
    0.76
     يتيمه
    0.75
    UnusedPrivate
    0.75
    Activations Density 1.335%

    No Known Activations