© 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. 849
    Prev
    Next
    INDEX
    Explanations

    terms related to technical or conceptual discussions about scientific theories and collaborations

    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
     COVID
    -1.61
    COVID
    -1.49
    . 
    -1.45
     covid
    -1.44
     Covid
    -1.42
    covid
    -1.41
     TikTok
    -1.34
     https
    -1.31
    Covid
    -1.31
     onboarding
    -1.28
    POSITIVE LOGITS
     idéia
    1.58
     daß
    1.25
     muß
    1.18
     läßt
    1.16
    myspace
    1.07
     Daß
    1.03
     Einfluß
    1.01
     biß
    0.97
     iPod
    0.97
     müßte
    0.95
    Activations Density 4.187%

    No Known Activations