© 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. 3418
    Prev
    Next
    INDEX
    Explanations

    references to personal possessions and living situations

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

    oneself or family members

    np_acts-logits-general · gemini-2.0-flash

    my, my project

    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
    のではないでしょうか
    -0.73
    或
    -0.67
    ведь
    -0.66
    出版年
    -0.66
     или
    -0.63
    Или
    -0.63
     quelconque
    -0.63
     or
    -0.63
     或
    -0.62
     ataupun
    -0.62
    POSITIVE LOGITS
     myself
    1.14
     my
    0.86
    myself
    0.86
     Myself
    0.71
     meines
    0.69
     minha
    0.67
     Italijanski
    0.66
     mijn
    0.64
     meus
    0.64
     meine
    0.63
    Activations Density 0.586%

    No Known Activations