© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 14842
    Prev
    Next
    INDEX
    Explanations

    references to specific lanes or pathways, particularly in a transportation context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تفصیلات
    -0.90
     jeunesse
    -0.80
    حياته
    -0.79
     soldati
    -0.77
    OCCURRED
    -0.77
     embri
    -0.75
    EDEFAULT
    -0.75
     XCTest
    -0.75
    appcompat
    -0.73
    حياتها
    -0.72
    POSITIVE LOGITS
     Lane
    1.61
     lanes
    1.52
     lane
    1.52
     LANE
    1.45
    Lane
    1.43
     Lanes
    1.35
    lane
    1.29
    LANE
    1.27
    lanes
    1.01
     Pene
    0.79
    Activations Density 0.007%

    No Known Activations