© 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. 14-GEMMASCOPE-RES-16K
    11. 10994
    Prev
    Next
    INDEX
    Explanations

    phrases related to forgetting, ignoring, or dismissing memories and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     voici
    -0.54
     katze
    -0.53
    Personendaten
    -0.52
     мәкалә
    -0.51
    estra
    -0.51
     الرخصة
    -0.51
    падает
    -0.50
     hObject
    -0.49
     fú
    -0.49
     Sauerstoff
    -0.48
    POSITIVE LOGITS
     pretend
    0.80
     forget
    0.77
     ignore
    0.77
     Ignore
    0.76
     ignor
    0.75
     ignored
    0.71
     ignorance
    0.68
     ignoring
    0.68
     ignores
    0.67
     forgets
    0.67
    Activations Density 0.258%

    No Known Activations