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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 13839
    Prev
    Next
    INDEX
    Explanations

    operations related to adding, creating, deleting, and managing updates in data structures

    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
    User
    -1.25
    人
    -0.99
    Date
    -0.72
    称为
    -0.65
    Time
    -0.57
    󠁮
    -0.57
    UserAgent
    -0.57
    UserGroup
    -0.56
    发表于
    -0.55
    ции
    -0.53
    POSITIVE LOGITS
     Administrativna
    0.47
    albert
    0.40
    تقاوى
    0.37
    acterium
    0.36
    neither
    0.35
     traditional
    0.34
    browserify
    0.33
    apprendre
    0.33
    peti
    0.33
    itolo
    0.33
    Activations Density 0.323%

    No Known Activations