© 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. 7558
    Prev
    Next
    INDEX
    Explanations

    biological and genetic technical terms

    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
    cB
    -0.47
     EK
    -0.47
     EH
    -0.47
     JH
    -0.45
     EG
    -0.44
    MigrationBuilder
    -0.44
     EF
    -0.44
    
    -0.43
     BM
    -0.43
     JC
    -0.43
    POSITIVE LOGITS
     surla
    0.59
     transfieras
    0.52
    aneity
    0.49
     vooz
    0.47
    errHandler
    0.46
     construcciones
    0.45
    uſe
    0.44
    pography
    0.43
    ysm
    0.43
     
    0.42
    Activations Density 1.506%

    No Known Activations