© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 13413
    Prev
    Next
    INDEX
    Explanations

    references to memory and forgetfulness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/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.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aDecoder
    -0.60
     Baal
    -0.57
     MongoClient
    -0.55
     Bautista
    -0.55
    renal
    -0.55
     photocopying
    -0.55
    ArrowToggle
    -0.54
    indication
    -0.54
    InjectMocks
    -0.54
    kész
    -0.53
    POSITIVE LOGITS
     remembered
    0.99
     forget
    0.94
     REMEMBER
    0.93
     remembers
    0.91
     Remember
    0.91
    Remind
    0.90
     remind
    0.90
    Remember
    0.89
     remembering
    0.89
     forgot
    0.89
    Activations Density 0.053%

    No Known Activations