© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 15295
    Prev
    Next
    INDEX
    Explanations

    the word "remember" and its variations, indicating a focus on recollection or memory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    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
    -0.86
    $")
    -0.86
    $.
    -0.81
    vidia
    -0.80
    Amicalement
    -0.70
    ?»
    -0.70
    britannien
    -0.69
    ⁎
    -0.68
    первых
    -0.65
     StatefulWidget
    -0.64
    POSITIVE LOGITS
     remember
    2.16
     remembers
    2.00
     REMEMBER
    2.00
     remembering
    1.93
     Remember
    1.91
     remembered
    1.89
    remember
    1.82
    Remember
    1.81
    Remembering
    1.51
     Remembering
    1.51
    Activations Density 0.040%

    No Known Activations