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

    Neuronpedia

    APICircuit 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. 16-GEMMASCOPE-RES-16K
    6. 6230
    Prev
    Next
    INDEX
    Explanations

    references to psychological distress and mental health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.97
    GEBURTSDATUM
    -0.93
     Roskov
    -0.90
    MigrationBuilder
    -0.87
    Hentet
    -0.84
    ViewFeatures
    -0.83
    BeginContext
    -0.79
    Portale
    -0.77
    TestingModule
    -0.77
     beginnetje
    -0.77
    POSITIVE LOGITS
     guilt
    0.73
     anxiety
    0.58
     self
    0.54
     Guilt
    0.52
     fears
    0.49
     perfection
    0.46
    perf
    0.45
     Anxiety
    0.44
    self
    0.44
     guil
    0.43
    Activations Density 0.201%

    No Known Activations