© 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. 2159
    Prev
    Next
    INDEX
    Explanations

    technical descriptions related to operational mechanisms and processes

    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
    enumi
    -0.78
     StatelessWidget
    -0.77
    Composable
    -0.69
     estekak
    -0.68
     snippetHide
    -0.66
    :✨
    -0.61
    HasForeignKey
    -0.58
    λίου
    -0.58
    Diwedd
    -0.57
     MainAxisSize
    -0.57
    POSITIVE LOGITS
     pouring
    1.26
     liquid
    1.23
     pour
    1.19
     poured
    1.19
     water
    1.18
     pump
    1.16
     pours
    1.15
     flow
    1.12
     Pour
    1.12
     fluid
    1.10
    Activations Density 0.797%

    No Known Activations