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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 35880
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords, specifically focusing on actions and data types

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    IBAction func, uint/uInt type declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     RoutedEventArgs
    -0.87
     HttpStatusCode
    -0.56
     oprot
    -0.52
    RegistryLite
    -0.51
    AnchorTagHelper
    -0.50
     createContext
    -0.49
    EndContext
    -0.47
    Географиясе
    -0.46
    OGND
    -0.46
    NamedQueries
    -0.46
    POSITIVE LOGITS
    Ӏ
    1.63
     SqlParameter
    1.18
     ITIS
    0.82
     chi̍t
    0.78
    Uint
    0.65
    SBATCH
    0.61
    IBAction
    0.60
     Uint
    0.57
     jadx
    0.56
     beginnetje
    0.54
    Activations Density 0.002%

    No Known Activations