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

    Neuronpedia

    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. 3-GEMMASCOPE-RES-16K
    11. 15676
    Prev
    Next
    INDEX
    Explanations

    instances of the word "forget."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     genomen
    -0.82
    styleType
    -0.77
    PreferredItem
    -0.73
    TintMode
    -0.71
     Rhein
    -0.69
    Население
    -0.69
    ClientSize
    -0.65
     sequelize
    -0.65
    ThroughAttribute
    -0.65
    jazdu
    -0.65
    POSITIVE LOGITS
     forget
    3.09
     forgetting
    2.67
     forgets
    2.63
    forget
    2.53
     Forget
    2.50
     FORGET
    2.48
     forgot
    2.33
    Forget
    2.27
     forgotten
    2.19
    forgotten
    1.78
    Activations Density 0.039%

    No Known Activations