© 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. 10-GEMMASCOPE-RES-16K
    11. 13462
    Prev
    Next
    INDEX
    Explanations

    instances of the word "remember," particularly in contexts of recalling past events or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.94
    $")
    -0.93
    )";
    -0.87
     ویکی‌پدیای
    -0.83
    ++
    -0.79
     "\""
    -0.78
    )");
    -0.77
    />";
    -0.77
    первых
    -0.77
    .";
    -0.76
    POSITIVE LOGITS
     remembers
    1.72
     remember
    1.68
     remembered
    1.66
     remembering
    1.63
     REMEMBER
    1.57
     Remember
    1.56
    Remember
    1.52
    remember
    1.47
     Remembering
    1.32
     remembrance
    1.31
    Activations Density 0.035%

    No Known Activations