© 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. 21-GEMMASCOPE-RES-16K
    11. 6341
    Prev
    Next
    INDEX
    Explanations

    keywords and structures related to computing and programming, specifically in context of data management and error handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "){
    -0.57
     poppies
    -0.52
     Adverti
    -0.52
     /\.(
    -0.52
     hobbit
    -0.51
     vnode
    -0.50
     presos
    -0.50
     YP
    -0.49
    كويكب
    -0.49
     raisin
    -0.49
    POSITIVE LOGITS
     *
    0.69
     any
    0.58
     I
    0.57
     string
    0.55
     ProtoMessage
    0.54
    opcional
    0.54
    Personensuche
    0.54
     int
    0.54
     CreateTagHelper
    0.53
     my
    0.52
    Activations Density 0.212%

    No Known Activations