© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 8905
    Prev
    Next
    INDEX
    Explanations

    references to personal growth and self-discovery

    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
    violi
    -0.48
     indisponible
    -0.45
     ejecut
    -0.44
     defaulted
    -0.42
     متعلقه
    -0.40
    raisemb
    -0.39
    ISODE
    -0.38
     incapacitated
    -0.38
     resultó
    -0.37
     Majefty
    -0.37
    POSITIVE LOGITS
     live
    0.69
     experience
    0.61
     conquer
    0.60
    Live
    0.58
     redis
    0.56
     overcome
    0.56
     Live
    0.55
     embrace
    0.54
     achieve
    0.53
     lived
    0.53
    Activations Density 0.396%

    No Known Activations