© 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. 13693
    Prev
    Next
    INDEX
    Explanations

    terms related to homelessness and support for vulnerable communities

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

    Homelessness and poverty

    np_acts-logits-general · gemini-2.0-flash

    homeless people

    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
     aDecoder
    -0.75
     AssemblyCulture
    -0.74
    verwijspagina
    -0.67
    matchCondition
    -0.64
    weds
    -0.63
     &___
    -0.61
     curd
    -0.59
     utafitiHapana
    -0.58
    fjspx
    -0.58
     blushing
    -0.58
    POSITIVE LOGITS
     homeless
    1.58
     homelessness
    1.41
     Homeless
    1.31
     sleeping
    1.07
     shelter
    0.97
     street
    0.95
     shelters
    0.89
     encamp
    0.86
     encampment
    0.86
     slept
    0.85
    Activations Density 0.135%

    No Known Activations