© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 0-GEMMASCOPE-RES-16K
    11. 10517
    Prev
    Next
    INDEX
    Explanations

    the presence of trademark and brand identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gorg
    -0.66
     Stiff
    -0.62
     fian
    -0.59
     culti
    -0.59
     defe
    -0.58
     dian
    -0.58
     brist
    -0.57
     cue
    -0.57
     solvent
    -0.56
     miser
    -0.56
    POSITIVE LOGITS
     actualidad
    0.57
     geschiedenis
    0.54
     actualizaciones
    0.53
     ciudades
    0.52
     regiones
    0.52
     votación
    0.51
     ampliación
    0.51
     renuncia
    0.49
     regioni
    0.49
     legislación
    0.49
    Activations Density 0.291%

    No Known Activations