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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1312
    Prev
    Next
    INDEX
    Explanations

    references to specific entities, particularly restaurants and products, in the context of programming structures

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

    Code, tags, or class-related tokens

    np_acts-logits-general · gemini-2.0-flash

    product, restaurant, book, airport, country

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    rawDesc
    -0.50
    IGraphics
    -0.48
    AutoScaleMode
    -0.48
    日閲覧
    -0.47
    principalTable
    -0.41
    存于互联网档案馆
    -0.40
    นี้
    -0.40
    انجليز
    -0.39
     jScrollPane
    -0.39
    testens
    -0.39
    POSITIVE LOGITS
     BoxDecoration
    0.60
     nakalista
    0.46
     cultivator
    0.45
     ViewHolder
    0.43
     BoxFit
    0.43
     AppCompatTheme
    0.42
    ocardial
    0.42
    ♼
    0.42
     Superhosts
    0.42
    reiro
    0.41
    Activations Density 0.312%

    No Known Activations