Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 110911
    Prev
    Next
    INDEX
    Explanations

    terms related to nationality and origins

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

    place of birth or nationality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    findpost
    -0.66
    saraba
    -0.53
    BufferException
    -0.51
    pherals
    -0.47
    DockStyle
    -0.47
    ьаж
    -0.46
    Personensuche
    -0.45
    цездатний
    -0.45
     يتيمه
    -0.45
     astore
    -0.44
    POSITIVE LOGITS
    nationality
    0.60
     étoit
    0.40
     wohnung
    0.39
     family
    0.38
     médical
    0.37
     nakalista
    0.35
     progrès
    0.35
    providedIn
    0.35
     inconnu
    0.35
     inconn
    0.34
    Activations Density 0.002%

    No Known Activations