© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 10715
    Prev
    Next
    INDEX
    Explanations

    references to societal threats and moral implications

    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
     doPost
    -0.42
     initComponents
    -0.39
    ✷
    -0.38
     Disposition
    -0.37
     Formats
    -0.36
    mingen
    -0.36
    ecera
    -0.36
     Grading
    -0.36
    ablon
    -0.35
     Baillargeon
    -0.35
    POSITIVE LOGITS
     symbol
    2.67
     symbolism
    2.31
     symbo
    2.30
     symbolic
    2.30
     symbolizes
    2.28
     symbols
    2.28
    symbol
    2.25
     symbolize
    2.25
     simbo
    2.23
     SYMBOL
    2.20
    Activations Density 0.445%

    No Known Activations