© 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. 31-GEMMASCOPE-RES-16K
    6. 7711
    Prev
    Next
    INDEX
    Explanations

    specific instances of physical actions or interactions between characters

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

    physically violent or aggressive actions.

    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
    +#+#
    -0.63
    Хьажоргаш
    -0.60
     Савезне
    -0.51
     '\\;'
    -0.51
    bootstrapcdn
    -0.51
    converse
    -0.50
    MessageTagHelper
    -0.50
     jScrollPane
    -0.50
     архивлан
    -0.49
    VIAF
    -0.49
    POSITIVE LOGITS
     instantly
    0.62
     quick
    0.61
     quickly
    0.59
     instantaneously
    0.59
     swiftly
    0.57
     startled
    0.57
     jerked
    0.57
     momentary
    0.57
     grabbed
    0.54
     sudden
    0.54
    Activations Density 0.325%

    No Known Activations