© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10652
    Prev
    Next
    INDEX
    Explanations

    structured data elements and their attributes

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

    "field" or "Field" labels

    np_acts-logits-general · gemini-2.0-flash

    field name or column

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    GeneratedCode
    -0.59
    AsyncResult
    -0.58
    EventQueue
    -0.56
    invokeLater
    -0.55
    wasan
    -0.53
    InvalidProtocol
    -0.52
    setzer
    -0.51
    StoryboardSegue
    -0.50
    AnchorTagHelper
    -0.49
    BorderSize
    -0.48
    POSITIVE LOGITS
     field
    1.40
     fields
    1.32
    Field
    1.20
    field
    1.19
    字段
    1.15
     Field
    1.15
     FIELD
    1.09
    FIELD
    1.09
     Fields
    1.06
    fields
    1.05
    Activations Density 0.863%

    No Known Activations