© 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 - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8882
    Prev
    Next
    INDEX
    Explanations

    instances of isolation or being alone

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

    solitude

    np_acts-logits-general · gemini-2.0-flash

    alone and loneliness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Relaciones
    -0.45
     Gobernador
    -0.43
    agissait
    -0.43
    ientôt
    -0.42
     typelib
    -0.40
     yii
    -0.39
    phosa
    -0.39
     musicales
    -0.39
    WriteTagHelper
    -0.37
     Grecs
    -0.37
    POSITIVE LOGITS
    Alone
    0.93
     Alone
    0.93
     loneliness
    0.88
     ALONE
    0.85
     lonely
    0.84
    alone
    0.84
     Solitude
    0.83
     solitude
    0.81
     solitary
    0.80
    lonely
    0.77
    Activations Density 0.203%

    No Known Activations