© 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. 8771
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing statements of fact, opinion, or intention

    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
     einerseits
    -0.65
     nämlich
    -0.62
     namelijk
    -0.60
    either
    -0.55
     either
    -0.55
     ابتدا
    -0.55
     nemlig
    -0.54
    Activités
    -0.51
     entweder
    -0.51
     Firstly
    -0.50
    POSITIVE LOGITS
     consequently
    1.12
     subsequently
    1.04
     consequent
    0.98
     therefore
    0.97
    sequently
    0.93
     consiguiente
    0.93
     importantly
    0.91
     subsequent
    0.91
     accordingly
    0.90
     thereby
    0.88
    Activations Density 1.307%

    No Known Activations