© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 14113
    Prev
    Next
    INDEX
    Explanations

    specific names and terms related to entities in a narrative or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     colgante
    -0.66
     chilena
    -0.65
     navideña
    -0.65
     alemana
    -0.63
     colombiana
    -0.63
     líquida
    -0.63
     compartida
    -0.62
     asiática
    -0.61
     orgánica
    -0.60
     británica
    -0.59
    POSITIVE LOGITS
    eo
    0.78
    evo
    0.71
     Ino
    0.70
     Argo
    0.70
    o
    0.69
    ſo
    0.69
     Cleo
    0.69
     Philo
    0.69
    airo
    0.69
    iro
    0.69
    Activations Density 1.686%

    No Known Activations