© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 8973
    Prev
    Next
    INDEX
    Explanations

    references to life and health statuses

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

    being alive and healthy

    np_acts-logits-general · gemini-2.0-flash

    alive and healthy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.29
    ApiModelProperty
    -0.28
     abstract
    -0.28
    glVertex
    -0.28
    遅い
    -0.27
     Fil
    -0.27
     ja
    -0.27
    ்கள
    -0.27
     endgül
    -0.27
     ar
    -0.26
    POSITIVE LOGITS
     alive
    0.94
    alive
    0.87
     ALIVE
    0.85
     Alive
    0.83
     healthy
    0.83
     intact
    0.82
     vitality
    0.81
     survives
    0.79
    元気
    0.78
    Alive
    0.77
    Activations Density 0.485%

    No Known Activations