© 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. 31-GEMMASCOPE-RES-16K
    11. 10040
    Prev
    Next
    INDEX
    Explanations

    terms related to caching and performance in computing systems

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

    proper nouns and brand names (particularly geographic locations, product names, and organizational titles).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    er
    -0.65
    y
    -0.50
    u
    -0.48
    ER
    -0.45
    -
    -0.44
    es
    -0.44
    ed
    -0.44
     
    -0.41
    or
    -0.39
    is
    -0.39
    POSITIVE LOGITS
     Савезне
    0.80
     ProtoMessage
    0.70
     desmotivaciones
    0.69
     '\\;'
    0.69
    ChildScrollView
    0.67
     müſſen
    0.67
    complexContent
    0.66
    parsedMessage
    0.66
     dieſer
    0.66
     ​​
    0.65
    Activations Density 1.958%

    No Known Activations