© 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. 6659
    Prev
    Next
    INDEX
    Explanations

    mentions of family members and relationships

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

    words related to children and offspring, particularly names and references to sons and daughters.

    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
    oinette
    -0.49
     Kathy
    -0.43
     Terri
    -0.41
     Sheryl
    -0.40
    Kathy
    -0.40
    Terri
    -0.39
     hag
    -0.39
     Janet
    -0.39
    DataPropertyName
    -0.38
     Barbara
    -0.38
    POSITIVE LOGITS
    Noah
    0.60
     Noah
    0.60
     Ethan
    0.59
     Dylan
    0.56
    Aidan
    0.56
     CreateTagHelper
    0.55
     Isabella
    0.55
     Elijah
    0.54
    Isabella
    0.54
     Aiden
    0.54
    Activations Density 0.071%

    No Known Activations