© 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. 4625
    Prev
    Next
    INDEX
    Explanations

    geographical features and locations

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

    directional words and geographical location descriptors (north, south, east, west, and related spatial terms).

    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
     supplé
    -0.38
    RenderAtEndOf
    -0.32
     remover
    -0.31
    FromNib
    -0.30
     neben
    -0.28
    सू
    -0.28
    ソー
    -0.27
    圆
    -0.27
     smo
    -0.26
     standing
    -0.26
    POSITIVE LOGITS
     north
    2.02
     south
    2.00
     west
    1.95
     east
    1.94
     eastward
    1.81
     northward
    1.74
     southward
    1.73
     northwest
    1.70
     westward
    1.70
     northeast
    1.69
    Activations Density 0.353%

    No Known Activations