Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2225
    Prev
    Next
    INDEX
    Explanations

    references to emotional and physical well-being

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

    Sadness and depression

    np_acts-logits-general · gemini-2.0-flash

    sadness and unhappiness

    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
     Issus
    -0.52
    Зноскі
    -0.49
    RFI
    -0.49
    젝
    -0.48
     interference
    -0.48
    袒
    -0.48
     Interference
    -0.48
    Lähteet
    -0.47
     harmless
    -0.46
     Heat
    -0.46
    POSITIVE LOGITS
     gloomy
    1.46
     gloom
    1.45
     depressing
    1.45
     depressed
    1.42
     melancholy
    1.36
     pessimistic
    1.33
     pessimism
    1.31
     somber
    1.30
     despond
    1.28
     sadness
    1.27
    Activations Density 0.340%

    No Known Activations