© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 1286
    Prev
    Next
    INDEX
    Explanations

    concepts related to preservation and maintenance of information, especially in the context of systems and processes

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

    frequency or commonality

    np_acts-logits-general · gemini-2.0-flash

    usually

    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
     hopefully
    -0.46
    確実に
    -0.45
     chắc
    -0.45
    obviously
    -0.45
     Surely
    -0.45
    hopefully
    -0.44
    Controllo
    -0.43
     certes
    -0.43
    carpa
    -0.42
     Obviously
    -0.42
    POSITIVE LOGITS
     kasarigan
    0.81
     suele
    0.66
     brukar
    0.62
     suelen
    0.60
     bý
    0.57
    原始内容存档于
    0.48
     бывает
    0.48
     vilja
    0.47
     usually
    0.44
     costuma
    0.43
    Activations Density 0.594%

    No Known Activations