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

    Neuronpedia

    Jacobian LensNEW
    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. 33-GEMMASCOPE-RES-16K
    11. 12476
    Prev
    Next
    INDEX
    Explanations

    video game terminology and features relevant to gameplay

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IPM
    -0.36
    batik
    -0.36
    JsonIgnore
    -0.35
    pageInfo
    -0.35
     neutr
    -0.35
    ayuno
    -0.34
    QM
    -0.33
     Peking
    -0.33
    Hon
    -0.32
    ália
    -0.32
    POSITIVE LOGITS
     console
    0.97
     consoles
    0.93
     Xbox
    0.88
     PS
    0.85
    IntoConstraints
    0.78
     Console
    0.77
    MessageTagHelper
    0.77
     xbox
    0.73
     PlayStation
    0.71
    Xbox
    0.70
    Activations Density 0.122%

    No Known Activations