© 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. 10-GEMMASCOPE-RES-16K
    11. 15429
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to rumors and hearsay

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 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
     explanatory
    -0.38
     zitten
    -0.38
     przem
    -0.38
     Crucifix
    -0.38
    autom
    -0.38
    vstack
    -0.38
    bestimmung
    -0.37
     unab
    -0.37
     sekali
    -0.37
    isak
    -0.37
    POSITIVE LOGITS
     rumor
    1.00
     rumors
    0.95
     rumour
    0.94
    噂
    0.86
     rumours
    0.85
    Rumors
    0.81
     rumores
    0.79
     Rumors
    0.75
     heard
    0.71
    Heard
    0.69
    Activations Density 0.372%

    No Known Activations