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. 33-GEMMASCOPE-RES-131K
    6. 65805
    Prev
    Next
    INDEX
    Explanations

    concepts related to child development and fostering independence

    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_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DBNull
    -0.56
    twimg
    -0.54
    migrationBuilder
    -0.54
    zzleHttp
    -0.52
    leneck
    -0.51
     nodeId
    -0.50
     Pingback
    -0.50
     bastard
    -0.50
     المعيارى
    -0.50
    ]^{-
    -0.49
    POSITIVE LOGITS
     learns
    0.62
     school
    0.61
     learning
    0.59
     learn
    0.59
     preschool
    0.58
     independence
    0.55
     playtime
    0.55
     adults
    0.54
     age
    0.53
     playground
    0.53
    Activations Density 0.049%

    No Known Activations