© 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. 33-GEMMASCOPE-RES-16K
    11. 661
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and research references

    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
     المعيارى
    -0.61
    Попис
    -0.52
    Eight
    -0.47
     ten
    -0.45
     Eight
    -0.42
     zehn
    -0.42
     Fifteen
    -0.40
     Ten
    -0.40
     eight
    -0.39
    Eleven
    -0.39
    POSITIVE LOGITS
     hundred
    0.93
    hundred
    0.82
     Hundred
    0.81
    一百
    0.81
     ninety
    0.77
     eighty
    0.76
     Ninety
    0.73
    Hundred
    0.73
    百
    0.72
     Eighty
    0.71
    Activations Density 1.659%

    No Known Activations