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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 5147
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to interaction and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     she
    -2.17
     она
    -1.67
     вона
    -1.45
    She
    -1.40
    she
    -1.31
    彼女は
    -1.20
     היא
    -1.20
     ella
    -1.04
     ela
    -1.02
    Она
    -0.98
    POSITIVE LOGITS
     her
    2.45
    her
    1.08
    她的
    0.88
     HER
    0.78
    Her
    0.74
     aceste
    0.66
     της
    0.65
     ее
    0.63
     ней
    0.63
    HER
    0.62
    Activations Density 0.348%

    No Known Activations