© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 7929
    Prev
    Next
    INDEX
    Explanations

    instances of the word "refer" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PackageName
    -0.73
    tése
    -0.66
    successfully
    -0.65
     ADP
    -0.64
    iast
    -0.63
    sth
    -0.61
    wps
    -0.61
    BlockSize
    -0.60
     outputStream
    -0.60
     dilaksanakan
    -0.60
    POSITIVE LOGITS
    Refer
    1.50
     refer
    1.46
     REFER
    1.43
     referral
    1.40
     Refer
    1.39
     referrals
    1.39
     referred
    1.34
     Referral
    1.29
     useRef
    1.25
     Referring
    1.25
    Activations Density 0.197%

    No Known Activations