© 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. 10443
    Prev
    Next
    INDEX
    Explanations

    words related to names and their meanings

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

    etymologies and word meanings, particularly from non-English languages.

    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
    setVerticalGroup
    -0.93
    enumii
    -0.93
     queſta
    -0.81
     myſelf
    -0.81
    ſelf
    -0.77
    adaptiveStyles
    -0.73
     pleaſure
    -0.71
     Majefty
    -0.70
     $_(
    -0.69
    aarrggbb
    -0.69
    POSITIVE LOGITS
     derived
    1.02
     meaning
    0.93
     derives
    0.87
     literally
    0.85
     derivation
    0.83
    derived
    0.82
     Derived
    0.82
     derive
    0.79
    Literally
    0.78
     Literally
    0.76
    Activations Density 0.197%

    No Known Activations