© 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. 9196
    Prev
    Next
    INDEX
    Explanations

    elements related to configuration in software coding

    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
    interopRequire
    -0.35
    saraba
    -0.35
    日閲覧
    -0.35
    Personendaten
    -0.34
    Παραπομπές
    -0.34
    ihnachts
    -0.33
     HasFactory
    -0.33
     Fam
    -0.31
     gefragt
    -0.31
    醐
    -0.31
    POSITIVE LOGITS
     Spring
    0.88
     spring
    0.84
    Spring
    0.80
     SPRING
    0.71
    spring
    0.68
    SPRING
    0.65
    SpringBoot
    0.63
     RestTemplate
    0.62
     Eureka
    0.60
    Discovery
    0.58
    Activations Density 0.247%

    No Known Activations