Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 8174
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to programming and online security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     éclairage
    -0.55
     câble
    -0.55
     jambe
    -0.54
     réservoir
    -0.53
     diamètre
    -0.52
     résistance
    -0.51
     refroidissement
    -0.51
     boîtier
    -0.51
     couvercle
    -0.50
     étui
    -0.50
    POSITIVE LOGITS
     disambiguazione
    0.67
    MigrationBuilder
    0.63
    :✨
    0.61
     Italijanski
    0.59
     ویکی‌پدی
    0.57
     rhestr
    0.56
     ModelExpression
    0.56
    gonic
    0.55
    WriteTagHelper
    0.55
     Numerade
    0.55
    Activations Density 0.098%

    No Known Activations