© 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. 8705
    Prev
    Next
    INDEX
    Explanations

    relationships and lineage within family structures

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

    descriptions of family size and composition, particularly focusing on counts of children and spouses in multi-generational family narratives.

    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
    lgari
    -0.52
    PreferredItem
    -0.49
     createSprite
    -0.47
     חיצוניים
    -0.46
     betweenstory
    -0.46
    뷔
    -0.45
    athione
    -0.45
    racuse
    -0.43
    łąd
    -0.43
    INCREF
    -0.42
    POSITIVE LOGITS
     children
    1.11
    children
    0.89
     kids
    0.89
     Children
    0.81
    Children
    0.81
     hijos
    0.80
     CHILDREN
    0.80
     kinderen
    0.80
     enfants
    0.79
     filhos
    0.78
    Activations Density 0.226%

    No Known Activations