© 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. 34-GEMMASCOPE-RES-16K
    11. 15858
    Prev
    Next
    INDEX
    Explanations

    sentences indicating outcomes or states related to processes and their evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shes
    -0.56
     theyre
    -0.52
     them
    -0.50
     youre
    -0.50
    səhifə
    -0.49
     linebacker
    -0.49
     flamenco
    -0.48
     arent
    -0.48
     multiplayer
    -0.48
     sedan
    -0.47
    POSITIVE LOGITS
     The
    1.06
     There
    0.91
     It
    0.90
     This
    0.90
     Some
    0.84
     In
    0.81
     When
    0.81
     For
    0.79
     Also
    0.78
     While
    0.78
    Activations Density 2.317%

    No Known Activations