Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 8727
    Prev
    Next
    INDEX
    Explanations

    references to individuals, particularly focusing on their roles and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kaarangay
    -0.54
    DockStyle
    -0.51
     незавершена
    -0.48
     XCTest
    -0.47
     propOrder
    -0.46
     neceff
    -0.45
    verifyException
    -0.45
    ChildScrollView
    -0.44
    ThroughAttribute
    -0.43
     Италијани
    -0.43
    POSITIVE LOGITS
     leaves
    0.87
    leaves
    0.76
     Leaves
    0.75
    Leaves
    0.71
     touched
    0.66
     leaf
    0.64
    leaf
    0.55
     deixa
    0.55
     touch
    0.55
     leave
    0.55
    Activations Density 0.099%

    No Known Activations