© 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. 33-GEMMASCOPE-RES-16K
    11. 524
    Prev
    Next
    INDEX
    Explanations

    phrases indicating financial or economic conditions and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     although
    -0.40
    ❘
    -0.33
     farsi
    -0.31
    belec
    -0.30
     ciudadana
    -0.29
     efforts
    -0.29
     kontaktieren
    -0.29
    </b>
    -0.29
    henswürdigkeiten
    -0.29
    ádza
    -0.28
    POSITIVE LOGITS
    ंदीखरीदारी
    0.88
    httphttps
    0.85
    MessageTagHelper
    0.73
     nahilalakip
    0.73
    msgTypes
    0.71
    IsMutable
    0.71
     informée
    0.71
    FieldBuilder
    0.71
    ⟬
    0.70
    verifyException
    0.69
    Activations Density 2.732%

    No Known Activations