© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 8908
    Prev
    Next
    INDEX
    Explanations

    references to homelessness and issues related to addiction and substance use

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

    near "homeless," "heroin," or harm reduction

    np_acts-logits-general · gemini-2.0-flash

    homelessness, beggars, heroin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rimas
    -0.24
     Âu
    -0.23
    impl
    -0.23
    भा
    -0.23
     قابل
    -0.23
    velope
    -0.23
     stood
    -0.23
    以
    -0.22
     stand
    -0.22
     х
    -0.22
    POSITIVE LOGITS
     homeless
    1.14
     Homeless
    1.09
     homelessness
    1.04
     hobo
    0.79
     queſta
    0.73
    Personendaten
    0.69
     miniaturka
    0.69
     EconPapers
    0.68
     shelters
    0.68
    astify
    0.68
    Activations Density 0.282%

    No Known Activations