© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 15267
    Prev
    Next
    INDEX
    Explanations

    references to charitable giving and fundraising campaigns

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

    campaigns, donations, or alumni

    np_acts-logits-general · gemini-2.0-flash

    alumni donations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilin
    -0.52
     moule
    -0.52
     AttributeSet
    -0.52
     newBuilder
    -0.52
     kohdetta
    -0.51
     виправивши
    -0.49
     متعلقه
    -0.47
    ute
    -0.46
    addPreferredGap
    -0.46
    lern
    -0.45
    POSITIVE LOGITS
     donor
    1.49
     donors
    1.39
     philanthropy
    1.39
     philanthropic
    1.31
    Donor
    1.28
     Donor
    1.26
    donor
    1.25
     Philanth
    1.25
     philanthrop
    1.23
     fundraising
    1.22
    Activations Density 0.130%

    No Known Activations