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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 9238
    Prev
    Next
    INDEX
    Explanations

    references to specific locations, events, and political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sometimes
    -0.48
    Sometimes
    -0.47
    chtest
    -0.46
     sometimes
    -0.46
     استنادى
    -0.45
     oftentimes
    -0.44
    帖最后由
    -0.44
     Occasionally
    -0.43
     Rarely
    -0.43
    Välislingid
    -0.43
    POSITIVE LOGITS
     prochain
    0.71
     someday
    0.69
     ASAP
    0.68
     prochaine
    0.66
     endlich
    0.65
    preferably
    0.65
     asap
    0.64
     preferably
    0.63
     prochaines
    0.62
     sooner
    0.60
    Activations Density 0.758%

    No Known Activations