© 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. 7571
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to software systems and their components

    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
    CloseOperation
    -0.53
    uxxxx
    -0.44
    CodedInputStream
    -0.44
    piram
    -0.43
     متعلقه
    -0.42
    +#+#
    -0.41
     iconTwitter
    -0.41
     @"/
    -0.41
    BitConverter
    -0.41
    exitRule
    -0.41
    POSITIVE LOGITS
     built
    1.01
     integrates
    0.98
     integrated
    0.96
     native
    0.94
     compatible
    0.94
    built
    0.93
     integrate
    0.93
     integrating
    0.91
     integration
    0.88
     compatibility
    0.88
    Activations Density 1.405%

    No Known Activations