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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 108270
    Prev
    Next
    INDEX
    Explanations

    concepts related to system failures and reliability in network architecture

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

    system failures or errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     libremente
    -0.38
     kasarigan
    -0.37
    setEditable
    -0.35
    ьаж
    -0.35
     geslacht
    -0.34
    adel
    -0.33
    Gun
    -0.32
     minted
    -0.32
    soort
    -0.32
     élar
    -0.32
    POSITIVE LOGITS
    WriteTagHelper
    0.67
     onPostExecute
    0.58
    kloped
    0.54
     оригіналу
    0.52
    তথ্যসূত্র
    0.52
     propOrder
    0.52
     ब्रेकडाउन
    0.51
    tonode
    0.49
     fault
    0.47
     personnel
    0.46
    Activations Density 0.053%

    No Known Activations