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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 70648
    Prev
    Next
    INDEX
    Explanations

    expressions related to personal growth and self-awareness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    consulté
    -0.52
    createTextNode
    -0.51
    AlterField
    -0.50
    findpost
    -0.47
    ถม
    -0.46
    fjspx
    -0.45
     GenerationType
    -0.45
    spyOn
    -0.45
     menim
    -0.45
    bkz
    -0.45
    POSITIVE LOGITS
     esternos
    0.49
     Keuangan
    0.47
     legales
    0.46
     infierno
    0.46
     sellado
    0.44
     rumbo
    0.42
     sols
    0.41
     productivo
    0.41
    URIDAD
    0.41
     originaux
    0.39
    Activations Density 0.032%

    No Known Activations