© 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. 25-GEMMASCOPE-RES-16K
    6. 2496
    Prev
    Next
    INDEX
    Explanations

    terms related to e-commerce usability and user experience enhancements

    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
    apimachinery
    -0.72
     فريبيس
    -0.67
    PrototypeOf
    -0.63
    IVENESS
    -0.57
     Poor
    -0.56
    HttpPut
    -0.56
    acing
    -0.55
     tỏ
    -0.54
    VIAF
    -0.54
     Ressource
    -0.53
    POSITIVE LOGITS
     stress
    1.21
     trouble
    1.13
     worry
    1.06
     hassle
    1.02
     pain
    1.00
     probleem
    0.92
     error
    0.90
     risk
    0.88
    stress
    0.86
     PAIN
    0.85
    Activations Density 0.489%

    No Known Activations