© 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-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 2145
    Prev
    Next
    INDEX
    Explanations

    aspects of support available to parents, particularly focusing on child care and economic factors

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

    references to support systems for parents and children in relation to education and social services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MemoryWarning
    -0.65
     Jugendlichen
    -0.60
    codegen
    -0.59
    bufio
    -0.58
    oa̍t
    -0.58
    WaitGroup
    -0.55
     Ninth
    -0.54
    blet
    -0.53
    estias
    -0.53
     Thirteenth
    -0.52
    POSITIVE LOGITS
     Early
    1.02
     childcare
    0.96
     preschool
    0.94
    Early
    0.93
     daycare
    0.92
     early
    0.87
     EARLY
    0.86
     Preschool
    0.85
     ECE
    0.84
    EARLY
    0.83
    Activations Density 0.126%

    No Known Activations