© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 4264
    Prev
    Next
    INDEX
    Explanations

    references to donations and philanthropic activities

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

    words and phrases related to donations and charitable giving.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ">//
    -0.44
    ContentAsync
    -0.36
    참고
    -0.35
    peria
    -0.34
     revanche
    -0.33
     пови
    -0.31
     Мексичка
    -0.31
    @[+][
    -0.29
     escar
    -0.28
    Referencie
    -0.28
    POSITIVE LOGITS
     donation
    2.58
     donate
    2.52
     donations
    2.50
     donating
    2.42
     donated
    2.33
     donors
    2.14
     donor
    2.11
     Donations
    2.11
     Donation
    2.09
    Donations
    2.02
    Activations Density 0.308%

    No Known Activations