© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 33
    Prev
    Next
    INDEX
    Explanations

    concepts related to education and personalized learning methods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Photocase
    -0.50
     resourceCulture
    -0.46
    出版年
    -0.43
    writeFieldEnd
    -0.42
    rungsseite
    -0.42
    Personensuche
    -0.39
    aarrggbb
    -0.39
    :✨
    -0.37
    
    -0.36
     createSlice
    -0.35
    POSITIVE LOGITS
     mathematical
    1.42
     mathematics
    1.41
     math
    1.36
     Mathematical
    1.28
     maths
    1.28
     Mathematics
    1.27
     mathematicians
    1.26
     mathematician
    1.23
     Math
    1.22
    数学
    1.22
    Activations Density 0.934%

    No Known Activations