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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 11448
    Prev
    Next
    INDEX
    Explanations

    statements and themes related to personal purpose and meaningful life experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.58
    LEncoder
    -0.45
    RectangleBorder
    -0.42
    leuth
    -0.40
    MessageOf
    -0.39
    ContentAlignment
    -0.39
     moletom
    -0.39
    expandindo
    -0.38
    APORE
    -0.36
    dersfield
    -0.36
    POSITIVE LOGITS
     life
    3.75
    life
    3.05
     Life
    2.86
     LIFE
    2.78
    Life
    2.77
     lives
    2.59
     vida
    2.56
    LIFE
    2.56
     жизни
    2.42
     Leben
    2.34
    Activations Density 1.005%

    No Known Activations