© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 3739
    Prev
    Next
    INDEX
    Explanations

    terms related to well-being and mental health

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

    following "well-" relating to health or feeling

    np_acts-logits-general · gemini-2.0-flash

    well-being

    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
    fjspx
    -0.58
    יסטוריה
    -0.52
    idge
    -0.49
    allenge
    -0.47
    יסטור
    -0.47
    atula
    -0.47
    下载附件
    -0.47
    azol
    -0.46
    ServletException
    -0.45
    lamydia
    -0.45
    POSITIVE LOGITS
    being
    1.19
     being
    1.18
    Being
    1.15
     Being
    1.10
     BEING
    1.02
     beings
    0.84
     bein
    0.79
     être
    0.72
    fare
    0.72
    être
    0.66
    Activations Density 0.141%

    No Known Activations