© 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. 24-GEMMASCOPE-RES-16K
    11. 4216
    Prev
    Next
    INDEX
    Explanations

    emotional connections and relationships between individuals

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

    Describes relationships between people

    np_acts-logits-general · gemini-2.0-flash

    connections and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    entierung
    -0.64
    ագրություններ
    -0.57
    orr
    -0.56
     IndexError
    -0.53
    örg
    -0.52
     bénévoles
    -0.50
    aggreg
    -0.50
     населения
    -0.49
    expandindo
    -0.49
    ünster
    -0.48
    POSITIVE LOGITS
     mutual
    1.04
     chemistry
    0.93
    mutual
    0.83
     friendship
    0.81
     shared
    0.81
    Mutual
    0.74
    Chemistry
    0.72
     mutually
    0.70
     bonded
    0.68
     sparks
    0.68
    Activations Density 0.236%

    No Known Activations