© 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. 19-GEMMASCOPE-RES-16K
    11. 4695
    Prev
    Next
    INDEX
    Explanations

    text that indicates the presence of bundles or collections, as well as the structural elements of written content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AnimationsModule
    -0.76
    ſelf
    -0.76
     ſch
    -0.73
     themſelves
    -0.70
     PackageManager
    -0.70
     saiba
    -0.70
     utafitiHapana
    -0.69
     ſtate
    -0.69
     Signalez
    -0.68
     greateſt
    -0.68
    POSITIVE LOGITS
     using
    0.75
     Using
    0.67
     experimenting
    0.66
     Took
    0.64
     took
    0.60
    Took
    0.59
     finished
    0.59
    Using
    0.58
     inspiration
    0.57
    Decided
    0.56
    Activations Density 0.327%

    No Known Activations