© 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. 629
    Prev
    Next
    INDEX
    Explanations

    references to Chinese or Japanese people and cultural contexts

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

    Names of nationalities/languages

    np_acts-logits-general · gemini-2.0-flash

    nationalities and countries

    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
    rungsseite
    -0.58
     typelib
    -0.50
     initState
    -0.45
    曖昧さ回避
    -0.45
    poptosis
    -0.43
     Gelände
    -0.43
     vueltas
    -0.43
    ValueStyle
    -0.43
     enthalpy
    -0.42
    stufe
    -0.42
    POSITIVE LOGITS
    Japanese
    0.83
    Indian
    0.83
    Chinese
    0.82
    Mexican
    0.82
     Indian
    0.82
    Russian
    0.82
    German
    0.81
     German
    0.81
     Russian
    0.80
    Spanish
    0.80
    Activations Density 0.254%

    No Known Activations