© 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. 15-GEMMASCOPE-RES-16K
    11. 1663
    Prev
    Next
    INDEX
    Explanations

    strings, function declarations, and methods that deal with various data structures and operations within programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵↵
    -0.24
     casada
    -0.23
    reactivex
    -0.22
    enschappelijke
    -0.20
    ();
    -0.20
     restricted
    -0.20
     single
    -0.20
    O
    -0.19
    ly
    -0.19
     (
    -0.19
    POSITIVE LOGITS
    ########.
    0.89
     GenerationType
    0.85
    featureID
    0.85
    niſſe
    0.81
     queſta
    0.80
    DockStyle
    0.79
     zuſammen
    0.78
     ſind
    0.78
     erſt
    0.78
     ſeinen
    0.77
    Activations Density 1.650%

    No Known Activations