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. 16-GEMMASCOPE-RES-16K
    6. 15893
    Prev
    Next
    INDEX
    Explanations

    terms related to immigration and its consequences

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

    Commas, ellipses, and sentence fragments

    np_acts-logits-general · gemini-2.0-flash

    Swedish or German modal verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     :')
    -0.98
    Alongside
    -0.95
     goddamn
    -0.93
     tryna
    -0.91
     prioritise
    -0.89
     Alongside
    -0.89
    …!
    -0.89
    Билгалдахарш
    -0.88
    Alright
    -0.87
     '{@
    -0.85
    POSITIVE LOGITS
     muß
    0.93
     skall
    0.93
     läßt
    0.81
    ・・・・・
    0.75
    luß
    0.74
     müßte
    0.73
     mußte
    0.72
     …..
    0.71
    .....
    0.67
     !!!!!
    0.66
    Activations Density 2.095%

    No Known Activations