© 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. 31-GEMMASCOPE-RES-16K
    11. 4992
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate availability, requests, and conditions for obtaining items or data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases indicating that something is available upon request or contact.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.48
    horabuena
    -0.47
     OFDb
    -0.47
    ismet
    -0.36
    |};
    -0.36
    }{*}{
    -0.35
     setLoading
    -0.35
    Życiorys
    -0.35
     hant
    -0.34
    rimônio
    -0.34
    POSITIVE LOGITS
     request
    1.27
     upon
    1.23
    upon
    1.17
    Upon
    1.13
     Upon
    1.11
     requested
    1.02
    request
    1.01
     UPON
    1.01
     Request
    0.99
    Request
    0.96
    Activations Density 0.374%

    No Known Activations