© 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. 12-GEMMASCOPE-RES-16K
    11. 1646
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to function and object creation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RegisterType
    -0.38
    SATURDAY
    -0.33
    TUESDAY
    -0.32
    MONDAY
    -0.30
     pymongo
    -0.29
     configureStore
    -0.28
    CPtr
    -0.28
    GOTREF
    -0.28
     Path
    -0.28
     Tuesday
    -0.27
    POSITIVE LOGITS
    adpleegd
    0.53
    OGND
    0.52
    setContentView
    0.51
     Biôgrafia
    0.49
     Theses
    0.47
    httphttps
    0.47
     вообще
    0.46
    ItemBackground
    0.46
    providedIn
    0.45
     vueltas
    0.44
    Activations Density 0.732%

    No Known Activations