© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10840
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causality and relationships involving "because of" and "the."

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

    "Because of"

    np_acts-logits-general · gemini-2.0-flash

    because of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     argint
    -0.46
    Trả
    -0.42
     esf
    -0.42
     itſelf
    -0.39
    lepší
    -0.39
     mediano
    -0.38
     ortodo
    -0.37
     espé
    -0.37
     équi
    -0.36
     houſe
    -0.36
    POSITIVE LOGITS
     wegen
    0.82
     dėl
    0.82
     vanwege
    0.79
    Благодаря
    0.78
     благодаря
    0.77
     devido
    0.76
     díky
    0.75
     بسبب
    0.73
    Debido
    0.73
    ůli
    0.72
    Activations Density 0.255%

    No Known Activations