© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 10159
    Prev
    Next
    INDEX
    Explanations

    instances of recent actions or announcements

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

    the word "just" used to describe something that recently happened or was completed.

    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
     nantinya
    -0.35
     initially
    -0.33
    บ้าง
    -0.33
     ابتدا
    -0.32
     inicialmente
    -0.32
     ?>
    -0.31
    ścic
    -0.31
     zunächst
    -0.31
    当初
    -0.30
    init
    -0.30
    POSITIVE LOGITS
    刚刚
    1.79
    剛剛
    1.77
     recently
    1.73
     appena
    1.71
     recién
    1.69
     just
    1.62
    recently
    1.59
    剛
    1.51
     Recently
    1.48
    Recently
    1.46
    Activations Density 0.309%

    No Known Activations