© 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. 21-GEMMASCOPE-RES-16K
    11. 11385
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols, indicating a focus on data, coding, or technical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.74
     препратки
    -0.66
    Personendaten
    -0.66
    parsedMessage
    -0.65
    تقاوى
    -0.64
    andExpect
    -0.63
    complexContent
    -0.63
    ngdoc
    -0.60
     الرياضيه
    -0.60
     useAppContext
    -0.59
    POSITIVE LOGITS
    0
    0.38
    2
    0.37
    1
    0.36
     New
    0.36
     Distinction
    0.35
    9
    0.35
     wyróż
    0.35
     gobier
    0.35
    7
    0.33
     spéciaux
    0.32
    Activations Density 0.471%

    No Known Activations