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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 39-GEMMASCOPE-RES-16K
    11. 3233
    Prev
    Next
    INDEX
    Explanations

    instances of people moving between floors or locations in a building, particularly using stairs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.66
    msgTypes
    -0.52
     الحره
    -0.50
     Protobuf
    -0.47
     oreilles
    -0.46
    
    -0.45
    AutoresizingMask
    -0.43
    SBATCH
    -0.43
    WriteBarrier
    -0.43
     Lash
    -0.43
    POSITIVE LOGITS
     stairs
    1.70
     staircase
    1.49
     stair
    1.49
     stairway
    1.45
     Stairs
    1.42
     Stair
    1.31
    Stair
    1.27
     steps
    1.27
     escaleras
    1.26
    stairs
    1.24
    Activations Density 0.344%

    No Known Activations