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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5049
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to donations and charitable contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.68
    OGND
    -0.49
     Fife
    -0.46
    SequentialGroup
    -0.45
    basicConfig
    -0.44
    PreExecute
    -0.43
    tieri
    -0.42
    setVerticalGroup
    -0.42
    Datuak
    -0.42
    idorm
    -0.42
    POSITIVE LOGITS
     donation
    1.47
     donate
    1.35
     Donation
    1.34
     donations
    1.34
     donated
    1.24
     donating
    1.24
     Donations
    1.24
    Donation
    1.24
    donation
    1.20
     Donate
    1.19
    Activations Density 0.147%

    No Known Activations