© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 42
    Prev
    Next
    INDEX
    Explanations

    programming constructs used in defining and manipulating data structures

    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
     newName
    -0.38
     isSelected
    -0.35
     totalCount
    -0.35
     isEnabled
    -0.34
     newList
    -0.34
     userList
    -0.32
     newUser
    -0.32
    styleUrls
    -0.32
     currentState
    -0.31
     onClose
    -0.31
    POSITIVE LOGITS
     prepare
    1.20
     make
    1.06
     build
    1.04
     generate
    1.04
     calculate
    1.03
     create
    1.03
    prepare
    0.98
     get
    0.97
     determine
    0.96
     collect
    0.93
    Activations Density 0.677%

    No Known Activations