© 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. 28-GEMMASCOPE-RES-16K
    11. 6186
    Prev
    Next
    INDEX
    Explanations

    key geographical and structural elements related to places and their significance

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

    Passage, entry, exit, or access points

    np_acts-logits-general · gemini-2.0-flash

    entrances, exits, and passages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     répertoire
    -0.36
    msgTypes
    -0.35
    Bibliote
    -0.32
    átiles
    -0.32
    ựng
    -0.32
    bosch
    -0.32
     réservoir
    -0.32
    rack
    -0.32
    uttgart
    -0.31
     receivers
    -0.31
    POSITIVE LOGITS
     entrance
    1.00
     access
    0.98
     gate
    0.93
     toegang
    0.91
     entry
    0.90
     exit
    0.90
     gateway
    0.90
     gateways
    0.88
     passage
    0.88
     Gate
    0.87
    Activations Density 0.562%

    No Known Activations