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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 2268
    Prev
    Next
    INDEX
    Explanations

    content related to personal struggles and emotional honesty

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

    support, healing, and sharing

    np_acts-logits-general · gemini-2.0-flash

    healing and expressing emotions

    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
    •Emotion Validation

    No Comments

    Negative Logits
    BitmapFactory
    -0.58
     quadrature
    -0.52
    UserScript
    -0.52
     parallax
    -0.50
    qrstuvwxyz
    -0.49
    xhtml
    -0.48
     гори
    -0.48
    :✨
    -0.47
    коном
    -0.47
     Magnetism
    -0.47
    POSITIVE LOGITS
     coping
    1.00
     cath
    0.94
     healing
    0.93
     Verarbeitung
    0.85
     processing
    0.84
     venting
    0.82
     therapeutic
    0.82
    coping
    0.82
     therapy
    0.82
     Coping
    0.80
    Activations Density 0.275%

    No Known Activations