© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 9503
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific data analysis and characterization

    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
    SequentialGroup
    -0.30
     planète
    -0.25
     actief
    -0.23
    ત્
    -0.23
    istan
    -0.23
     flèche
    -0.22
     pensée
    -0.21
    गे
    -0.21
     незавершена
    -0.21
     tokoh
    -0.21
    POSITIVE LOGITS
     creation
    1.53
    creation
    1.33
     formation
    1.26
     acquisition
    1.23
     management
    1.22
     manipulation
    1.20
     removal
    1.19
     retrieval
    1.18
     preparation
    1.18
     maximization
    1.16
    Activations Density 2.615%

    No Known Activations