© 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. 2-GEMMASCOPE-RES-16K
    11. 9293
    Prev
    Next
    INDEX
    Explanations

    section references in academic texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    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
    -0.75
    OGND
    -0.65
    AsUp
    -0.57
    Życiorys
    -0.50
    Autoritní
    -0.49
    Gast
    -0.44
    WriteTagHelper
    -0.44
    Tikang
    -0.43
    entation
    -0.43
    vanna
    -0.43
    POSITIVE LOGITS
    Sec
    3.53
     Sec
    3.48
    sec
    3.41
     sec
    3.23
    SEC
    2.59
     SEC
    2.45
    secu
    1.93
     SECUR
    1.88
    SECUR
    1.87
     secular
    1.86
    Activations Density 0.212%

    No Known Activations