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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 10914
    Prev
    Next
    INDEX
    Explanations

    identifiers or references to court cases and legal documents

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

    "Id" or "id" followed by a punctuation mark

    np_acts-logits-general · gemini-2.0-flash

    id or Id in citations and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.81
    \}\\
    -0.74
    Controllo
    -0.67
    laştır
    -0.58
    wered
    -0.56
    Denne
    -0.55
    wer
    -0.54
    coaster
    -0.54
    י
    -0.53
    spesies
    -0.53
    POSITIVE LOGITS
     يتيمه
    0.80
    iosync
    0.66
     card
    0.64
    ثيق
    0.64
    RenderAtEndOf
    0.62
     AssemblyCompany
    0.60
    initWithFrame
    0.60
     disambiguazione
    0.59
    entyfik
    0.58
    Hentet
    0.58
    Activations Density 0.177%

    No Known Activations