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. 16105
    Prev
    Next
    INDEX
    Explanations

    references to death and remembrance of deceased individuals

    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
    ValueGenerated
    -0.35
     decote
    -0.34
     тол
    -0.34
     kill
    -0.33
     membunuh
    -0.33
    反应过来
    -0.32
     namorados
    -0.32
     totalSupply
    -0.32
     ATTENTION
    -0.30
    aneity
    -0.30
    POSITIVE LOGITS
     departed
    0.88
     resting
    0.71
     Rest
    0.70
     depart
    0.69
     peacefully
    0.67
     AssemblyCompany
    0.66
     gone
    0.65
     transitioned
    0.65
    depar
    0.65
    Rest
    0.65
    Activations Density 0.133%

    No Known Activations