© 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. 13-GEMMASCOPE-RES-16K
    11. 6577
    Prev
    Next
    INDEX
    Explanations

    phrases related to ideal or perfect attributes and recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Meksiku
    -0.49
     Administrativna
    -0.47
    GEBURTSDATUM
    -0.46
     kasarigan
    -0.43
     BorderSide
    -0.42
     jezelf
    -0.40
    ctory
    -0.40
    Nuorodos
    -0.39
     admitir
    -0.39
    ➯
    -0.39
    POSITIVE LOGITS
     ideal
    0.74
    Ideal
    0.70
     ideale
    0.68
    ideal
    0.67
     Ideal
    0.67
     idéal
    0.60
     suited
    0.58
     IDEAL
    0.57
     ideales
    0.57
    suited
    0.55
    Activations Density 0.417%

    No Known Activations