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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1846
    Prev
    Next
    INDEX
    Explanations

    concepts related to life and its various aspects, including planning, experiences, and mortality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     McGregor
    -0.51
    retudo
    -0.49
    <bos>
    -0.46
     pernicious
    -0.46
     cucchia
    -0.45
     Chamber
    -0.44
     cater
    -0.44
     amarelo
    -0.44
     barbers
    -0.44
     tenders
    -0.43
    POSITIVE LOGITS
    Life
    1.33
    life
    1.32
    LIFE
    1.31
     LIFE
    1.24
     Life
    1.20
     life
    1.19
    lifes
    1.02
     vida
    0.92
    Vida
    0.90
    Lif
    0.90
    Activations Density 0.072%

    No Known Activations