© 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. 34-GEMMASCOPE-RES-16K
    11. 11012
    Prev
    Next
    INDEX
    Explanations

    comparative expressions indicating relative importance or strength

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OrNil
    -0.48
     GenerationType
    -0.46
    المكان
    -0.45
     ExecuteAsync
    -0.45
    oa̍t
    -0.45
    ManagedBean
    -0.43
    出版年
    -0.42
    IsMutable
    -0.41
    mobileqq
    -0.41
     AssemblyTitle
    -0.40
    POSITIVE LOGITS
     ever
    4.34
    ever
    3.20
     EVER
    3.13
    Ever
    2.98
     Ever
    2.95
    EVER
    2.63
     jemals
    2.30
     ooit
    2.00
     jamais
    1.86
     pernah
    1.69
    Activations Density 0.496%

    No Known Activations