© 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. 0-GEMMASCOPE-RES-16K
    11. 9790
    Prev
    Next
    INDEX
    Explanations

    terms related to realistic simulations and theoretical modeling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wpi
    -0.35
     expandable
    -0.33
     endocrine
    -0.32
    dropna
    -0.32
     voed
    -0.32
     lặng
    -0.31
    person
    -0.31
    NFPA
    -0.31
     prochains
    -0.30
     Gesundheit
    -0.29
    POSITIVE LOGITS
     CreateTagHelper
    0.84
    featureID
    0.82
    realistic
    0.82
     realistic
    0.81
     theoretical
    0.80
     Realistic
    0.77
    ↹
    0.77
    theoretical
    0.75
    Realistic
    0.75
     qualitative
    0.74
    Activations Density 2.100%

    No Known Activations