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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-GEMMASCOPE-RES-16K
    6. 8679
    Prev
    Next
    INDEX
    Explanations

    mentions of medical conditions and degenerative issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كومونز
    -0.75
    ("}\
    -0.52
    felves
    -0.52
    disambiguation
    -0.50
     المعيارى
    -0.50
     brief
    -0.50
     kasarigan
    -0.50
    setof
    -0.49
    Allister
    -0.48
     unlocked
    -0.46
    POSITIVE LOGITS
     aging
    1.25
     vieill
    1.13
     Aging
    1.11
     ageing
    1.08
    Aging
    1.03
     aged
    0.95
     envejec
    0.94
     age
    0.89
     Aged
    0.82
    Aged
    0.75
    Activations Density 0.474%

    No Known Activations