© 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. 33-GEMMASCOPE-RES-16K
    11. 8100
    Prev
    Next
    INDEX
    Explanations

    mentions of powerful, destructive entities or forces

    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
    +:+
    -0.44
    nsics
    -0.41
     תח
    -0.41
     fieldNum
    -0.40
    untura
    -0.40
     crouch
    -0.38
    marginRight
    -0.37
     ū
    -0.37
    中毒
    -0.36
    🤸
    -0.36
    POSITIVE LOGITS
     ancient
    0.58
     powerful
    0.56
     Chaos
    0.55
     god
    0.54
     God
    0.53
    expandindo
    0.53
     primordial
    0.52
    mordial
    0.51
    ancient
    0.51
     cosmological
    0.50
    Activations Density 0.565%

    No Known Activations