© 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. 6868
    Prev
    Next
    INDEX
    Explanations

    themes related to societal structures and issues of power dynamics

    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
     AssemblyCompany
    -0.43
     ModelExpression
    -0.30
    робнее
    -0.28
     Th
    -0.27
     Hope
    -0.26
    ături
    -0.26
    IgnoreCase
    -0.24
                               
    -0.24
     Journal
    -0.24
     Hunter
    -0.24
    POSITIVE LOGITS
     queſta
    0.76
    PerformLayout
    0.70
    boiling
    0.69
     auroit
    0.68
     ſeine
    0.67
    bending
    0.66
    stepper
    0.65
    scaling
    0.63
     laſſen
    0.63
     podjela
    0.63
    Activations Density 0.587%

    No Known Activations