© 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. 1-GEMMASCOPE-RES-16K
    11. 7840
    Prev
    Next
    INDEX
    Explanations

    actions and processes that denote cause and effect

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     isolato
    -0.22
     сда
    -0.19
    határoz
    -0.18
     utilisez
    -0.17
     tekem
    -0.17
     orina
    -0.16
     bawa
    -0.16
     edit
    -0.16
     comiendo
    -0.16
     submit
    -0.16
    POSITIVE LOGITS
     HasFactory
    0.90
     otomatig
    0.84
     Autorizaciones
    0.83
    astify
    0.82
     ſei
    0.80
    Datuak
    0.79
    قایناق‌لار
    0.78
     surla
    0.78
    IntoConstraints
    0.78
     ویکی‌پدیا
    0.77
    Activations Density 1.033%

    No Known Activations