© 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. 7806
    Prev
    Next
    INDEX
    Explanations

    variables and expressions related to programming or mathematical equations

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

    the word "variable" across different contexts (programming code, technical documentation, and academic papers).

    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
     EconPapers
    -0.76
    Personendaten
    -0.72
    %)$
    -0.66
     مرئيه
    -0.66
    Tikang
    -0.58
    NameInMap
    -0.58
     ​​
    -0.57
     utafitiHapana
    -0.57
    twimg
    -0.56
     propOrder
    -0.54
    POSITIVE LOGITS
    ه
    0.84
    a
    0.82
    ा
    0.60
    en
    0.54
    ا
    0.47
    ה
    0.45
    i
    0.45
    aze
    0.44
    ta
    0.42
    łby
    0.42
    Activations Density 1.868%

    No Known Activations