© 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. 12978
    Prev
    Next
    INDEX
    Explanations

    elements of suspense and mystery in storytelling

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

    superlatives and emphatic language expressing high praise or strong emotional intensity.

    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
    MessageOf
    -0.63
    Datuak
    -0.61
     فريبيس
    -0.61
    didSet
    -0.56
    liosis
    -0.52
     BorderSide
    -0.50
    uvwxyz
    -0.49
     Wikimedijinoj
    -0.49
     تضيفلها
    -0.49
    VideoCapture
    -0.48
    POSITIVE LOGITS
     Available
    0.66
    Available
    0.63
     Visit
    0.62
     available
    0.62
    available
    0.57
     dostęp
    0.55
     visit
    0.54
    AVAILABLE
    0.53
     AVAILABLE
    0.52
    Purchase
    0.50
    Activations Density 0.235%

    No Known Activations