© 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
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4428
    Prev
    Next
    INDEX
    Explanations

    string manipulation functions and methods in programming code

    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
     HasFactory
    -0.61
    TemporalType
    -0.52
    béco
    -0.50
     للاسماء
    -0.49
     Chwiliwch
    -0.48
    ContainerState
    -0.47
    HasAnnotation
    -0.46
     CGSize
    -0.46
    graphique
    -0.45
    MLLoader
    -0.45
    POSITIVE LOGITS
    indexOf
    0.70
    lastIndexOf
    0.70
    startsWith
    0.56
    split
    0.56
    startswith
    0.52
    querySelectorAll
    0.51
    RequestMapping
    0.50
    StartsWith
    0.49
    endsWith
    0.47
    rawDesc
    0.47
    Activations Density 0.161%

    No Known Activations