© 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. 21-GEMMASCOPE-RES-16K
    11. 12799
    Prev
    Next
    INDEX
    Explanations

    terms related to physical properties and behaviors of systems, particularly in the context of stability and dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unauthorized
    -0.40
     pagkak
    -0.34
     AssemblyVersion
    -0.34
    getLatitude
    -0.33
     receita
    -0.33
     Jungen
    -0.32
     жу
    -0.32
     ldc
    -0.32
     Händen
    -0.31
     omdat
    -0.31
    POSITIVE LOGITS
    tagHelperRunner
    0.71
    IntoConstraints
    0.60
    URLException
    0.56
    RotationOrder
    0.49
    gnore
    0.48
    tvguidetime
    0.47
    sizeCache
    0.47
    LEncoder
    0.46
    arakhand
    0.46
    erals
    0.45
    Activations Density 0.914%

    No Known Activations