Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 1127
    Prev
    Next
    INDEX
    Explanations

    references to the concept of being "old" or discussions about aging

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyTitle
    -0.95
    脚注の使い方
    -0.92
     springfox
    -0.91
     незавершена
    -0.90
    IsContent
    -0.90
    hésite
    -0.85
    XtraReports
    -0.84
     <=",
    -0.82
     Autorizaciones
    -0.82
     jSON
    -0.81
    POSITIVE LOGITS
     OLD
    1.41
     old
    1.40
     Old
    1.38
    Old
    1.26
     fashioned
    1.10
     vieux
    1.02
    old
    1.01
     Oldham
    0.94
    OLD
    0.92
     vieja
    0.91
    Activations Density 0.043%

    No Known Activations