© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 3882
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to patent applications and scientific methods

    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
    脚注の使い方
    -0.85
    Personendaten
    -0.84
    principalTable
    -0.78
    ніципалі
    -0.75
    出版年
    -0.68
    GEBURTSDATUM
    -0.67
     defaultstate
    -0.67
     ExecuteAsync
    -0.65
    styleable
    -0.65
    DeleteBehavior
    -0.64
    POSITIVE LOGITS
     expensive
    1.15
     costly
    1.13
    expensive
    0.90
     Expensive
    0.87
     pricey
    0.83
     spend
    0.75
     cumbersome
    0.74
     costs
    0.72
     wasted
    0.72
     wasting
    0.71
    Activations Density 0.735%

    No Known Activations