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. 13-GEMMASCOPE-RES-16K
    6. 12969
    Prev
    Next
    INDEX
    Explanations

    numbers and code-like sequences within the text

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

    technical, non‑natural‑language tokens such as uppercase identifiers, dense numerals/punctuation, hex/code addresses, and LaTeX-style math notation typical of logs and formulas.

    oai_token-act-pair · gpt-5Triggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     سكانية
    -0.85
    verwijspagina
    -0.84
     createSlice
    -0.71
     externi
    -0.70
    ----</
    -0.68
     resourceCulture
    -0.67
    ernalia
    -0.67
    Dichloropropene
    -0.65
     وتسجيلات
    -0.62
     henvisninger
    -0.62
    POSITIVE LOGITS
     Réponses
    0.60
     Administrativna
    0.57
    mother
    0.45
    بالإ
    0.44
     Dad
    0.43
     Fab
    0.43
    Statistiche
    0.43
    djangoproject
    0.42
     *++
    0.42
     Mom
    0.42
    Activations Density 3.031%

    No Known Activations