© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 10537
    Prev
    Next
    INDEX
    Explanations

    instances of the word "separate" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.74
    SequentialGroup
    -0.73
    tvguidetime
    -0.70
     témoig
    -0.65
    operation
    -0.60
     queſta
    -0.60
     operation
    -0.58
    iſen
    -0.58
     esternos
    -0.57
     ddelwed
    -0.57
    POSITIVE LOGITS
     separate
    1.26
    separate
    1.12
     Separate
    1.11
    Separate
    1.08
     seperate
    0.96
     separately
    0.84
     separado
    0.68
     terpisah
    0.68
     SEPAR
    0.60
     отдель
    0.58
    Activations Density 0.053%

    No Known Activations