© 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. 15126
    Prev
    Next
    INDEX
    Explanations

    terms related to offers, acceptance, and transaction processes

    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
    bootstrapcdn
    -0.42
    UnusedPrivate
    -0.40
    RefNanny
    -0.38
    ột
    -0.36
    transQ
    -0.36
    liceerd
    -0.33
     NSCoder
    -0.32
    NameInMap
    -0.31
     AssemblyTitle
    -0.30
     centrifugal
    -0.30
    POSITIVE LOGITS
     accept
    3.86
     acceptance
    3.84
     accepting
    3.73
     accepted
    3.66
     accepts
    3.50
     Accept
    3.48
     ACCEPT
    3.44
     Acceptance
    3.42
     Accepting
    3.41
    Accept
    3.27
    Activations Density 1.114%

    No Known Activations