© 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. 1664
    Prev
    Next
    INDEX
    Explanations

    concepts related to living in the moment and the interplay of past, present, and future

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

    moments when past, present, and future are discussed together in temporal contexts.

    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
     FileInputStream
    -0.37
     CURIAM
    -0.32
     betweenstory
    -0.31
    容
    -0.31
    BagLayout
    -0.31
    unteer
    -0.31
    hésitez
    -0.30
    má
    -0.30
    ajuato
    -0.30
    дко
    -0.30
    POSITIVE LOGITS
     present
    2.75
     Present
    2.44
    Present
    2.44
    present
    2.42
     PRESENT
    2.30
     presente
    2.08
     présent
    2.06
     prefent
    1.92
     presentes
    1.89
    PRESENT
    1.85
    Activations Density 0.463%

    No Known Activations