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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 77
    Prev
    Next
    INDEX
    Explanations

    terms related to charitable donations and philanthropy

    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
     فريبيس
    -0.78
    DotNetBar
    -0.61
     Audiodateien
    -0.60
     ErrIntOverflow
    -0.59
    rungsseite
    -0.58
     ویکی‌پدی
    -0.55
    calyptic
    -0.55
    ensement
    -0.55
     &___
    -0.54
    OrBuilder
    -0.52
    POSITIVE LOGITS
     gifts
    1.18
     giving
    1.03
     Giving
    1.01
    Gifts
    1.01
     gift
    1.01
     Gifts
    1.00
     donations
    0.99
     donors
    0.98
    Giving
    0.95
    gifts
    0.94
    Activations Density 0.204%

    No Known Activations