© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 23659
    Prev
    Next
    INDEX
    Explanations

    instances of the word "remember" and its variations, focusing on recollection and memories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    remember the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exploration
    -0.38
     pleaſure
    -0.37
     explorations
    -0.36
    yu
    -0.36
     Exploration
    -0.35
     indisponible
    -0.35
    Expl
    -0.35
     امريكا
    -0.35
     explore
    -0.35
     nonUne
    -0.35
    POSITIVE LOGITS
     remember
    1.48
     remembers
    1.41
     Remember
    1.36
     remembering
    1.35
    remember
    1.34
     remembered
    1.32
    Remember
    1.27
     REMEMBER
    1.23
     recall
    1.16
     Recall
    1.16
    Activations Density 0.031%

    No Known Activations