© 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. 39-GEMMASCOPE-RES-16K
    11. 4054
    Prev
    Next
    INDEX
    Explanations

    words and phrases in Slavic languages, particularly those related to greetings and farewells

    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
    外
    -0.29
    上
    -0.28
    za
    -0.28
     πρά
    -0.27
    la
    -0.27
    ال
    -0.26
    un
    -0.26
    ob
    -0.26
    S
    -0.25
    de
    -0.25
    POSITIVE LOGITS
     Houſe
    0.97
     Monfieur
    0.86
    ロウィン
    0.85
     Anſ
    0.85
     CanadaChoose
    0.82
     transfieras
    0.81
     Inſ
    0.80
    webElementXpaths
    0.79
     myſelf
    0.79
     houſe
    0.78
    Activations Density 0.035%

    No Known Activations