© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 24662
    Prev
    Next
    INDEX
    Explanations

    themes related to isolation and quarantine during a pandemic

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

    pandemic lockdown depression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     път
    -0.40
     ogen
    -0.39
    ęp
    -0.39
    LookAnd
    -0.38
    ={`
    -0.37
    cire
    -0.36
     kosme
    -0.36
    jalanan
    -0.36
    always
    -0.35
    Bjs
    -0.35
    POSITIVE LOGITS
     boredom
    0.74
     quarantined
    0.73
     isolation
    0.71
     Isolation
    0.67
     quarantine
    0.67
     virtuel
    0.66
    Isolation
    0.66
    isolation
    0.65
     virtual
    0.64
     confinement
    0.63
    Activations Density 0.017%

    No Known Activations