© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 30-GEMMASCOPE-RES-16K
    11. 13226
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causation or conclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding "instances", "cases", "way", "therefore", or "thus"

    np_acts-logits-general · gemini-2.0-flash

    conclusions and consequences expressed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     infatti
    -0.54
     bowiem
    -0.51
     Infórmanos
    -0.49
    tagHelperRunner
    -0.49
     however
    -0.47
     nämlich
    -0.47
     namelijk
    -0.46
     nemlig
    -0.45
     però
    -0.44
    LookAnd
    -0.44
    POSITIVE LOGITS
    IsContent
    0.51
     they
    0.49
     gives
    0.48
     includes
    0.47
    >--}}
    0.45
     brings
    0.45
     has
    0.44
     används
    0.44
    าก็
    0.44
     involves
    0.43
    Activations Density 0.414%

    No Known Activations