© 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. 37-GEMMASCOPE-RES-16K
    11. 4361
    Prev
    Next
    INDEX
    Explanations

    specific programming constructs and their relationships within class definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.58
    PerformLayout
    -0.56
     utafitiHapana
    -0.55
    makeConstraints
    -0.54
    kháu
    -0.54
    
    -0.53
     Biôgrafia
    -0.53
    ftagPool
    -0.52
    OGND
    -0.50
     <<<<<<<<<<<<<<
    -0.48
    POSITIVE LOGITS
     mainly
    0.43
    (){}
    0.41
     chiefly
    0.38
     above
    0.38
    mainly
    0.33
    RECEIVE
    0.33
     mostly
    0.32
     primarily
    0.32
     nowhere
    0.31
    Tidak
    0.31
    Activations Density 0.115%

    No Known Activations