© 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. 0-GEMMASCOPE-RES-16K
    6. 1921
    Prev
    Next
    INDEX
    Explanations

    instances of the word "exceed" or its variations, often indicating limits or thresholds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     miniaturka
    -0.75
     avoient
    -0.71
     المعيارى
    -0.69
     autorytatywna
    -0.69
    exitRule
    -0.66
     étoient
    -0.63
     ainfi
    -0.62
     étoit
    -0.61
     chrétien
    -0.61
     katholischen
    -0.60
    POSITIVE LOGITS
     exceed
    0.58
     exceeds
    0.44
     Map
    0.44
    MAP
    0.43
     MAP
    0.43
     exceeded
    0.42
    Map
    0.41
    ://
    0.38
    map
    0.37
    Portail
    0.37
    Activations Density 0.262%

    No Known Activations