© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 9718
    Prev
    Next
    INDEX
    Explanations

    personal relationships and interactions

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

    after personal pronouns

    np_acts-logits-general · gemini-2.0-flash

    belong or own

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.48
     semakin
    -0.48
    Enders
    -0.47
     continues
    -0.46
    )++;
    -0.46
    esgue
    -0.46
     immer
    -0.46
    клопе
    -0.46
    anias
    -0.46
    ipot
    -0.45
    POSITIVE LOGITS
     belong
    1.12
     belonged
    1.11
     belongs
    1.01
     pertenece
    0.97
     owns
    0.90
     appartiennent
    0.89
     pertenecen
    0.88
    belong
    0.85
     owned
    0.84
     pertence
    0.84
    Activations Density 0.529%

    No Known Activations