© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 18556
    Prev
    Next
    INDEX
    Explanations

    references to components or items in code or programming contexts

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

    explicit item references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PDOException
    -0.52
     Vand
    -0.49
    URLEncoder
    -0.48
     Wald
    -0.48
     Bold
    -0.48
    örd
    -0.47
    Wald
    -0.47
    oug
    -0.47
     للمعارف
    -0.46
    oudre
    -0.45
    POSITIVE LOGITS
    Item
    2.27
     Item
    1.58
    ITEM
    1.13
     ITEM
    1.05
     item
    0.98
    DataItem
    0.95
     getItem
    0.89
    BarItem
    0.89
    item
    0.88
    getItem
    0.87
    Activations Density 0.005%

    No Known Activations