© 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. 35-GEMMASCOPE-RES-16K
    6. 6289
    Prev
    Next
    INDEX
    Explanations

    references to age groups, particularly focusing on comparisons between young and old generations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Wife
    -0.33
     forbear
    -0.31
    FormTagHelper
    -0.31
    memoized
    -0.31
    iNdEx
    -0.31
     Wife
    -0.31
    μβρίου
    -0.29
    AfterClass
    -0.29
     تانيه
    -0.29
    HttpEntity
    -0.29
    POSITIVE LOGITS
     young
    3.44
    young
    3.13
    Young
    2.86
     YOUNG
    2.80
     younger
    2.77
     Young
    2.73
     jeune
    2.61
     jungen
    2.56
     joven
    2.55
     jeunes
    2.55
    Activations Density 0.654%

    No Known Activations