© 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. 6748
    Prev
    Next
    INDEX
    Explanations

    references to sibling relationships and family dynamics

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

    family relationships and sibling references.

    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
    inWeight
    -0.49
    makeConstraints
    -0.45
    Carriera
    -0.45
    ACHUSET
    -0.43
    BorderLayout
    -0.42
     gabbana
    -0.41
    帖最后由
    -0.41
    convertView
    -0.40
     مشين
    -0.40
    tinyos
    -0.40
    POSITIVE LOGITS
     brother
    2.80
     brothers
    2.61
     siblings
    2.59
     sibling
    2.58
     sister
    2.55
    brother
    2.41
     sisters
    2.38
     Brother
    2.30
    brothers
    2.22
    Brother
    2.19
    Activations Density 0.246%

    No Known Activations