© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 16457
    Prev
    Next
    INDEX
    Explanations

    instances of the word "later" and its variations in relation to time

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

    temporal progression of events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     vooraf
    -0.80
     heretofore
    -0.79
     sebelumnya
    -0.79
    Personendaten
    -0.75
     préalable
    -0.74
     earlier
    -0.74
     previous
    -0.73
     wcześ
    -0.73
     previously
    -0.72
     wcześniej
    -0.72
    POSITIVE LOGITS
     became
    0.49
     diventato
    0.46
     becomes
    0.44
     выясни
    0.44
     regretted
    0.43
     become
    0.43
     devenu
    0.41
    became
    0.40
     becoming
    0.39
     refined
    0.39
    Activations Density 0.071%

    No Known Activations