© 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. 31-GEMMASCOPE-RES-16K
    11. 7553
    Prev
    Next
    INDEX
    Explanations

    characters or symbols from various scripts and languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    non-Latin script characters and unicode symbols from various writing systems.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -1.09
    Autoritní
    -1.08
    GEBURTSDATUM
    -1.08
    RegressionTest
    -1.08
     autorytatywna
    -1.00
    Jeografia
    -0.99
     '\\;'
    -0.94
     zwiſchen
    -0.93
     CreateTagHelper
    -0.93
    ſſung
    -0.92
    POSITIVE LOGITS
     decisión
    0.36
     ciudadanía
    0.33
     Técnica
    0.33
     prioridad
    0.32
     válida
    0.31
     encargada
    0.30
     instrucción
    0.30
     enseñanza
    0.30
     posibilidad
    0.30
     votación
    0.29
    Activations Density 0.005%

    No Known Activations