© 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. 20-GEMMASCOPE-RES-16K
    6. 10556
    Prev
    Next
    INDEX
    Explanations

    expressions related to charitable donations and fundraising efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Acts of donating to charity or for a cause

    np_acts-logits-general · gemini-2.0-flash

    donations to charities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ब्रेकडाउन
    -0.60
    +#+#
    -0.59
     myſelf
    -0.55
    ✭✭
    -0.54
    RTLE
    -0.51
     administracy
    -0.51
     argint
    -0.51
     snabbt
    -0.50
     Allociné
    -0.50
     tranquille
    -0.49
    POSITIVE LOGITS
     charity
    1.93
     charities
    1.69
    charity
    1.56
     charitable
    1.47
     Charity
    1.43
    Charity
    1.34
     Charities
    1.23
     donation
    1.14
     Charitable
    1.11
     donate
    1.10
    Activations Density 0.147%

    No Known Activations