© 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. 5-GEMMASCOPE-RES-16K
    11. 6877
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to divorce and healing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     isolado
    -0.97
     EconPapers
    -0.93
     Normdatei
    -0.89
    tahankan
    -0.86
     againſt
    -0.85
     referenties
    -0.85
    OGND
    -0.84
     Efq
    -0.82
     Houſe
    -0.81
     validamos
    -0.81
    POSITIVE LOGITS
     wounds
    0.80
     Wounds
    0.78
     Rau
    0.77
     trauma
    0.75
     hum
    0.73
    heil
    0.72
     wound
    0.72
     Trauma
    0.69
     divorce
    0.68
     diver
    0.67
    Activations Density 0.104%

    No Known Activations