© 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. 6423
    Prev
    Next
    INDEX
    Explanations

    references to family relationships and personal connections

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

    personal pronouns and possessive adjectives indicating family relationships and genealogical connections.

    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
     MenuView
    -0.43
     parachoque
    -0.41
     SqlCommand
    -0.39
     للاسماء
    -0.39
     recherchez
    -0.39
    findpost
    -0.39
    MLLoader
    -0.39
     TÉCN
    -0.38
    glTexCoord
    -0.35
     sanitarias
    -0.35
    POSITIVE LOGITS
     great
    1.09
    great
    1.01
     Great
    0.95
    Great
    0.95
    GREAT
    0.82
     GREAT
    0.80
     Gt
    0.55
     greats
    0.53
    Вели
    0.53
     utafitiHapana
    0.52
    Activations Density 0.114%

    No Known Activations