© 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. 33-GEMMASCOPE-RES-16K
    11. 9160
    Prev
    Next
    INDEX
    Explanations

    themes of collective experience and personal challenges in life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     հղումներ
    -0.70
     Signalez
    -0.68
    DockStyle
    -0.67
    HostException
    -0.66
     AssemblyTitle
    -0.66
    ConstraintMaker
    -0.65
     فريبيس
    -0.63
    HideFlags
    -0.62
    Хьажоргаш
    -0.60
     surla
    -0.59
    POSITIVE LOGITS
     owe
    0.69
     owes
    0.68
     need
    0.49
     owed
    0.47
     needs
    0.47
     cannot
    0.47
     can
    0.47
     mustn
    0.45
     CAN
    0.42
     alone
    0.41
    Activations Density 0.397%

    No Known Activations