© 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. 9-GEMMASCOPE-RES-16K
    11. 8760
    Prev
    Next
    INDEX
    Explanations

    instances of the word "per" related to measurements or rates

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

    The neuron detects the word "per" when used as a preposition indicating rates, standards, or distributions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ruine
    -0.48
     Majefty
    -0.48
    SerializedSize
    -0.45
     itſelf
    -0.43
     raiſ
    -0.40
     faſt
    -0.39
    Биография
    -0.39
    GOTREF
    -0.39
     nuest
    -0.39
    zzleHttp
    -0.38
    POSITIVE LOGITS
     per
    2.09
     Per
    1.87
    Per
    1.75
     PER
    1.57
    per
    1.52
    PER
    1.23
     Perkins
    1.05
     Perkin
    1.05
    PerPage
    0.95
     Perr
    0.95
    Activations Density 0.112%

    No Known Activations