© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 536
    Prev
    Next
    INDEX
    Explanations

    structured data related to programming and configuration settings

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

    instances of equal signs followed by important details or instructions related to software configurations

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

    express or implied

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    SequentialGroup
    -0.80
    EDEFAULT
    -0.72
    InitVars
    -0.71
    AccessorTable
    -0.70
     createState
    -0.65
    StoryboardSegue
    -0.65
    مراجع
    -0.64
    UrlResolution
    -0.63
    ControllerTest
    -0.61
     تعدى
    -0.61
    POSITIVE LOGITS
     restricting
    0.55
     restricted
    0.53
    Title
    0.51
    kson
    0.48
    Restricted
    0.48
    iced
    0.47
    Restrict
    0.47
    restricted
    0.47
    小行星
    0.47
     restring
    0.46
    Activations Density 0.010%

    No Known Activations