Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4605
    Prev
    Next
    INDEX
    Explanations

    phrases related to organizations and teamwork

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows words like "from" or "with."

    np_acts-logits-general · gemini-2.0-flash

    applications encountered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     weirdly
    -1.19
     tryna
    -1.16
    idk
    -1.10
     idk
    -1.09
     shitty
    -1.08
    Alongside
    -1.06
     tbh
    -1.01
     fucked
    -1.00
     dodgy
    -0.99
     prioritise
    -0.98
    POSITIVE LOGITS
     muß
    1.04
     skall
    0.99
     läßt
    0.95
     idéia
    0.87
     mußte
    0.85
     daß
    0.83
     Usted
    0.80
     sculptured
    0.78
    luß
    0.77
     müßte
    0.76
    Activations Density 3.733%

    No Known Activations