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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 103137
    Prev
    Next
    INDEX
    Explanations

    themes of personal growth and redemption

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

    Text segments that describe personal growth, values acquisition, or character development - particularly moments where characters find meaning, confidence, or learn important life lessons.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    Билгалдахарш
    -0.47
     Vikipedi
    -0.41
     propOrder
    -0.38
    NOPQRST
    -0.37
    Autoritní
    -0.37
    Personensuche
    -0.37
    CPtr
    -0.37
    BufferException
    -0.36
    IContainer
    -0.33
     etab
    -0.33
    POSITIVE LOGITS
    HasAnnotation
    0.50
    expandindo
    0.48
    BindingResult
    0.47
     friendship
    0.47
     amitié
    0.45
     lesson
    0.45
     Friendship
    0.45
     amistad
    0.45
    Friendship
    0.44
     onStop
    0.44
    Activations Density 0.080%

    No Known Activations