© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 6258
    Prev
    Next
    INDEX
    Explanations

    themes of memory and remembrance in relation to personal and collective experiences

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

    memory and remembrance

    np_acts-logits-general · gemini-2.0-flash

    lasting memories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     informée
    -0.54
    IsContent
    -0.43
     ब्रेकडाउन
    -0.42
    tolua
    -0.42
    сылкі
    -0.42
    出版年
    -0.40
     expon
    -0.39
    jsxFileName
    -0.39
     cover
    -0.38
     approxim
    -0.38
    POSITIVE LOGITS
     forever
    0.82
     indelible
    0.75
     навсегда
    0.73
     memory
    0.72
    forever
    0.71
     memories
    0.66
     FOREVER
    0.63
    memory
    0.58
    Forever
    0.57
     permanently
    0.56
    Activations Density 0.174%

    No Known Activations