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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 5513
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions and related websites

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

    websites and locations

    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
    تقاوى
    -0.69
    rawDesc
    -0.62
     يتيمه
    -0.58
     nahilalakip
    -0.57
    httphttps
    -0.53
    Personendaten
    -0.53
     للمعارف
    -0.50
    dafx
    -0.50
    WithIOException
    -0.49
    EndContext
    -0.48
    POSITIVE LOGITS
    getSystemService
    0.46
    sidemargin
    0.42
    StandardCharsets
    0.42
    addAttribute
    0.37
    KommentareTeilen
    0.37
    EndInit
    0.37
     MainAxisSize
    0.36
    IsPostBack
    0.36
     Superintendent
    0.35
     getItemId
    0.35
    Activations Density 0.003%

    No Known Activations