© 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. 11440
    Prev
    Next
    INDEX
    Explanations

    references to benefits, rights, and advantages related to individuals or entities in legal or clinical contexts

    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
     nakalista
    -0.46
    gdala
    -0.40
     &___
    -0.38
    atel
    -0.36
    :✨
    -0.36
    Herzliche
    -0.35
    gente
    -0.35
     surla
    -0.35
     Vork
    -0.35
    GoogleApiClient
    -0.35
    POSITIVE LOGITS
     benefit
    3.61
     benefits
    3.28
    benefit
    3.22
    Benefit
    3.09
     Benefit
    3.05
    benefits
    2.91
     benefited
    2.88
     benefiting
    2.88
     Benefits
    2.86
     benefitted
    2.78
    Activations Density 0.823%

    No Known Activations