© 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. 11075
    Prev
    Next
    INDEX
    Explanations

    structural elements of narrative, such as punctuation and sentence breaks

    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
     muß
    -1.19
     läßt
    -1.17
     idéia
    -1.08
     daß
    -1.01
     Надо
    -0.94
     müßte
    -0.89
     Moslem
    -0.87
     надо
    -0.86
     !!!!!
    -0.85
    Надо
    -0.85
    POSITIVE LOGITS
    Alongside
    1.16
     Alongside
    1.14
     ⁠
    1.00
     incentiv
    0.93
     alongside
    0.91
     Notably
    0.88
    Personensuche
    0.87
    Ultimately
    0.86
     Ultimately
    0.85
    “[
    0.81
    Activations Density 0.325%

    No Known Activations