© 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. 5652
    Prev
    Next
    INDEX
    Explanations

    phrases related to helping vulnerable populations and charitable acts

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

    Helping the needy and vulnerable

    np_acts-logits-general · gemini-2.0-flash

    helping the poor

    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
    gatsby
    -0.54
     вме
    -0.49
    RegistryLite
    -0.47
    espa
    -0.45
    PreInfinity
    -0.43
     tölt
    -0.43
    rat
    -0.42
     arbitrators
    -0.42
     jsPsych
    -0.42
    AndroidJUnit
    -0.41
    POSITIVE LOGITS
     needy
    1.29
     disadvantaged
    1.28
     vulnerable
    1.24
     homeless
    1.22
     poor
    1.13
     destitute
    1.11
     indigent
    1.10
     disabled
    1.08
     orphaned
    1.05
     orphans
    1.04
    Activations Density 0.379%

    No Known Activations