© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 11467
    Prev
    Next
    INDEX
    Explanations

    expressions related to environmental and societal contexts surrounding individual experiences

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

    "live in" or similar phrases

    np_acts-logits-general · gemini-2.0-flash

    living in environments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +};
    -0.39
    minecraftforge
    -0.38
    matta
    -0.38
     bedankt
    -0.34
    teness
    -0.34
    neh
    -0.34
     egyes
    -0.33
    lijck
    -0.33
    jerne
    -0.33
     Dire
    -0.33
    POSITIVE LOGITS
     amid
    1.29
     amidst
    1.29
     surrounded
    1.16
     Amid
    1.13
    Amid
    1.06
    amid
    0.95
    在一个
    0.88
     într
    0.86
     rodeado
    0.85
     umgeben
    0.77
    Activations Density 0.991%

    No Known Activations